Search

With the remarkable recent progress on learning deep generative models, it becomes increasingly interesting to develop models for controllable image synthesis from reconfigurable structured inputs. This paper focuses on a recently emerged task, layout-to-image, whose goal is to learn generative models for synthesizing photo-realistic images from a spatial layout (i.e., object bounding boxes configured in an image lattice) and its style codes (i.e., structural and appearance variations encoded by latent vectors). This paper first proposes an intuitive paradigm for the task, layout-to-mask-to-image, which learns to unfold object masks in a weakly-supervised way based on an input layout and object style codes. The layout-to-mask component deeply interacts with layers in the generator network to bridge the gap between an input layout and synthesized images. Then, this paper presents a method built on Generative Adversarial Networks (GANs) for the proposed layout-to-mask-to-image synthesis with layout and style control at both image and object levels. The controllability is realized by a proposed novel Instance-Sensitive and Layout-Aware Normalization (ISLA-Norm) scheme. A layout semi-supervised version of the proposed method is further developed without sacrificing performance. In experiments, the proposed method is tested in the COCO-Stuff dataset and the Visual Genome dataset with state-of-the-art performance obtained. [ABSTRACT FROM AUTHOR]

The vanilla Few-shot Learning (FSL) learns to build a classifier for a new concept from one or very few target examples, with the general assumption that source and target classes are sampled from the same domain. Recently, the task of Cross-Domain Few-Shot Learning (CD-FSL) aims at tackling the FSL where there is a huge domain shift between the source and target datasets. Extensive efforts on CD-FSL have been made via either directly extending the meta-learning paradigm of vanilla FSL methods, or employing massive unlabeled target data to help learn models. In this paper, we notice that in the CD-FSL task, the few labeled target images have never been explicitly leveraged to inform the model in the training stage. However, such a labeled target example set is very important to bridge the huge domain gap. Critically, this paper advocates a more practical training scenario for CD-FSL. And our key insight is to utilize a few labeled target data to guide the learning of the CD-FSL model. Technically, we propose a novel Generalized Meta-learning based Feature-Disentangled Mixup network, namely GMeta-FDMixup. We make three key contributions of utilizing GMeta-FDMixup to address CD-FSL. Firstly, we present two mixup modules – mixup-P and mixup-M that help facilitate utilizing the unbalanced and disjoint source and target datasets. These two novel modules enable diverse image generation for training the model on the source domain. Secondly, to narrow the domain gap explicitly, we contribute a novel feature disentanglement module that learns to decouple the domain-irrelevant and domain-specific features. By stripping the domain-specific features, we alleviate the negative effects caused by the domain inductive bias. Finally, we repurpose a new contrastive learning module, dubbed ConL. ConL prevents the model from only capturing category-related features via introducing contrastive loss. Thus, the generalization ability on novel categories is improved. Extensive experimental results on two benchmarks show the superiority of our setting and the effectiveness of our method. Code and models will be released. [ABSTRACT FROM AUTHOR]

Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and annotating large-scale datasets, as a subset of unsupervised learning methods, self-supervised learning methods are proposed to learn general image and video features from large-scale unlabeled data without using any human-annotated labels. This paper provides an extensive review of deep learning-based self-supervised general visual feature learning methods from images or videos. First, the motivation, general pipeline, and terminologies of this field are described. Then the common deep neural network architectures that used for self-supervised learning are summarized. Next, the schema and evaluation metrics of self-supervised learning methods are reviewed followed by the commonly used datasets for images, videos, audios, and 3D data, as well as the existing self-supervised visual feature learning methods. Finally, quantitative performance comparisons of the reviewed methods on benchmark datasets are summarized and discussed for both image and video feature learning. At last, this paper is concluded and lists a set of promising future directions for self-supervised visual feature learning. [ABSTRACT FROM AUTHOR]

This paper addresses the task of set prediction using deep feed-forward neural networks. A set is a collection of elements which is invariant under permutation and the size of a set is not fixed in advance. Many real-world problems, such as image tagging and object detection, have outputs that are naturally expressed as sets of entities. This creates a challenge for traditional deep neural networks which naturally deal with structured outputs such as vectors, matrices or tensors. We present a novel approach for learning to predict sets with unknown permutation and cardinality using deep neural networks. In our formulation we define a likelihood for a set distribution represented by a) two discrete distributions defining the set cardinally and permutation variables, and b) a joint distribution over set elements with a fixed cardinality. Depending on the problem under consideration, we define different training models for set prediction using deep neural networks. We demonstrate the validity of our set formulations on relevant vision problems such as: 1) multi-label image classification where we outperform the other competing methods on the PASCAL VOC and MS COCO datasets, 2) object detection, for which our formulation outperforms popular state-of-the-art detectors, and 3) a complex CAPTCHA test, where we observe that, surprisingly, our set-based network acquired the ability of mimicking arithmetics without any rules being coded. [ABSTRACT FROM AUTHOR]

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with $L$ L layers have $L$ L connections—one between each layer and its subsequent layer—our network has $\frac{L(L+1)}{2}$ L (L + 1) 2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, encourage feature reuse and substantially improve parameter efficiency. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less parameters and computation to achieve high performance. [ABSTRACT FROM AUTHOR]

Pathology analysis is crucial to precise cancer diagnoses and the succeeding treatment plan as well. To detect abnormality in histopathology images with prevailing patch-based convolutional neural networks (CNNs), contextual information often serves as a powerful cue. However, as whole-slide images (WSIs) are characterized by intense morphological heterogeneity and extensive tissue scale, a straightforward visual span to a larger context may not well capture the information closely associated with the focal patch. In this paper, we propose a novel pixel-offset based patch-location method to identify high-representative tissues, with a CNN backbone. Pathology Deformable Conditional Random Field (PDCRF) is proposed to learn the offsets and weights of neighboring contexts in a spatial-adaptive manner, to search for high-representative patches. A CNN structure with the localized patches as training input is then capable of consistently reaching superior classification outcomes for histology images. Overall, the proposed method has achieved state-of-the-art performance, in terms of the test classification accuracy improvement to the baseline by 1.15-2.60%, 0.78-1.78%, and 1.47-2.18% on TCGA public datasets of TCGA-STAD, TCGA-COAD, and TCGA-READ respectively. It also achieves 88.95% test accuracy and 0.920 test AUC on Camelyon 16. To show the effectiveness of the proposed framework on downstream tasks, we take a further step by incorporating an active learning model, which noticeably reduces the number of manual annotations by PDCRF to reach a parallel patch-based histology classifier. [ABSTRACT FROM AUTHOR]

As power systems are undergoing a significant transformation with more uncertainties, less inertia and closer to operation limits, there is increasing risk of large outages. Thus, there is an imperative need to enhance grid emergency control to maintain system reliability and security. Towards this end, great progress has been made in developing deep reinforcement learning (DRL) based grid control solutions in recent years. However, existing DRL-based solutions have two main limitations: 1) they cannot handle well with a wide range of grid operation conditions, system parameters, and contingencies; 2) they generally lack the ability to fast adapt to new grid operation conditions, system parameters, and contingencies, limiting their applicability for real-world applications. In this paper, we mitigate these limitations by developing a novel deep meta-reinforcement learning (DMRL) algorithm. The DMRL combines the meta strategy optimization together with DRL, and trains policies modulated by a latent space that can quickly adapt to new scenarios. We test the developed DMRL algorithm on the IEEE 300-bus system. We demonstrate fast adaptation of the meta-trained DRL polices with latent variables to new operating conditions and scenarios using the proposed method, which achieves superior performance compared to the state-of-the-art DRL and model predictive control (MPC) methods. [ABSTRACT FROM AUTHOR]

Deep learning has greatly promoted the development of multi-view stereo in recent years. However, how to measure the reliability of the estimated depth map for practical applications and make reasonable depth hypothesis sampling for the cost volume building in the coarse-to-fine architecture are still unresolved crucial problems. To this end, an Uncertainty Guided multi-view Network (UGNet) is proposed in this paper. In order to enable the network to perceive the uncertainty, an uncertainty-aware loss function is introduced, which not only can infer uncertainty implicitly in an unsupervised manner but also can reduce the bad impact of high uncertainty regions and the erroneous labels in the training set during training. Moreover, an uncertainty-based depth hypothesis sampling strategy is further proposed to adaptively determine the depth search range of each pixel for finer stages, which helps to generate more rational depth intervals compared with other methods and build more compact cost volumes without redundancy. Experimental results on DTU dataset, BlendedMVS dataset, Tanks and Temples dataset and ETH3D high-res benchmark show that our method achieves promising reconstruction results compared with other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper, we consider how to incorporate psychophysical measurements of human visual perception into the loss function of a deep neural network being trained for a recognition task, under the assumption that such information can reduce errors. As a case study to assess the viability of this approach, we look at the problem of handwritten document transcription. While good progress has been made towards automatically transcribing modern handwriting, significant challenges remain in transcribing historical documents. Here we describe a general enhancement strategy, underpinned by the new loss formulation, which can be applied to the training regime of any deep learning-based document transcription system. Through experimentation, reliable performance improvement is demonstrated for the standard IAM and RIMES datasets for three different network architectures. Further, we go on to show feasibility for our approach on a new dataset of digitized Latin manuscripts, originally produced by scribes in the Cloister of St. Gall in the the 9th century. [ABSTRACT FROM AUTHOR]

With substantial amount of time, resources and human (team) efforts invested to explore and develop successful deep neural networks (DNN), there emerges an urgent need to protect these inventions from being illegally copied, redistributed, or abused without respecting the intellectual properties of legitimate owners. Following recent progresses along this line, we investigate a number of watermark-based DNN ownership verification methods in the face of ambiguity attacks, which aim to cast doubts on the ownership verification by forging counterfeit watermarks. It is shown that ambiguity attacks pose serious threats to existing DNN watermarking methods. As remedies to the above-mentioned loophole, this paper proposes novel passport-based DNN ownership verification schemes which are both robust to network modifications and resilient to ambiguity attacks. The gist of embedding digital passports is to design and train DNN models in a way such that, the DNN inference performance of an original task will be significantly deteriorated due to forged passports. In other words, genuine passports are not only verified by looking for the predefined signatures, but also reasserted by the unyielding DNN model inference performances. Extensive experimental results justify the effectiveness of the proposed passport-based DNN ownership verification schemes. Code is available at https://github.com/kamwoh/DeepIPR. [ABSTRACT FROM AUTHOR]

Deep learning based models have excelled in many computer vision tasks and appear to surpass humans’ performance. However, these models require an avalanche of expensive human labeled training data and many iterations to train their large number of parameters. This severely limits their scalability to the real-world long-tail distributed categories, some of which are with a large number of instances, but with only a few manually annotated. Learning from such extremely limited labeled examples is known as Few-Shot Learning (FSL). Different to prior arts that leverage meta-learning or data augmentation strategies to alleviate this extremely data-scarce problem, this paper presents a statistical approach, dubbed Instance Credibility Inference (ICI) to exploit the support of unlabeled instances for few-shot visual recognition. Typically, we repurpose the self-taught learning paradigm to predict pseudo-labels of unlabeled instances with an initial classifier trained from the few shot and then select the most confident ones to augment the training set to re-train the classifier. This is achieved by constructing a (Generalized) Linear Model (LM/GLM) with incidental parameters to model the mapping from (un-)labeled features to their (pseudo-)labels, in which the sparsity of the incidental parameters indicates the credibility of the corresponding pseudo-labeled instance. We rank the credibility of pseudo-labeled instances along the regularization path of their corresponding incidental parameters, and the most trustworthy pseudo-labeled examples are preserved as the augmented labeled instances. This process is repeated until all the unlabeled samples are included in the expanded training set. Theoretically, under the conditions of restricted eigenvalue, irrepresentability, and large error, our approach is guaranteed to collect all the correctly-predicted pseudo-labeled instances from the noisy pseudo-labeled set. Extensive experiments under two few-shot settings show the effectiveness of our approach on four widely used few-shot visual recognition benchmark datasets including miniImageNet, tieredImageNet, CIFAR-FS, and CUB. Code and models are released at https://github.com/Yikai-Wang/ICI-FSL. [ABSTRACT FROM AUTHOR]

In order to retain more feature information of local areas on a point cloud, local grouping and subsampling are the necessary data structuring steps in most hierarchical deep learning models. Due to the disorder nature of the points in a point cloud, the significant time cost may be consumed when grouping and subsampling the points, which consequently results in poor scalability. This paper proposes a fast data structuring method called PSNet (Point Structuring Net). PSNet transforms the spatial features of the points and matches them to the features of local areas in a point cloud. PSNet achieves grouping and sampling at the same time while the existing methods process sampling and grouping in two separate steps (such as using FPS plus kNN). PSNet performs feature transformation pointwise while the existing methods uses the spatial relationship among the points as the reference for grouping. Thanks to these features, PSNet has two important advantages: 1) the grouping and sampling results obtained by PSNet is stable and permutation invariant; and 2) PSNet can be easily parallelized. PSNet can replace the data structuring methods in the mainstream point cloud deep learning models in a plug-and-play manner. We have conducted extensive experiments. The results show that PSNet can improve the training and inference speed significantly while maintaining the model accuracy. [ABSTRACT FROM AUTHOR]

Models for image semantics understanding, such as deep learning (DL) models and mathematical models, are often trained on specific dataset or configured with specific parameters. When deploying such models on new tasks in a different test environment, it requires considerable effort to re-train the model or extensive expertise to tune the parameters. In this paper, we propose a smart reinforcement learning (RL) agent that could learn to tune parameters automatically to enhance model performance. The learning process is formulated as a generic control task for parameter adjustment, and applied to two use scenarios: (1) image attributes tuning to improve object detection performance on fixed DL model, and (2) parameter tuning of the mathematical model (Level Set) for image segmentation. We design a novel dynamic threshold mechanism in a multi-branch RL agent to effectively tune parameters of image qualities (for object detection) and Level Set models (for object segmentation). We conduct experiments on Pascal-VOC testing set, MS COCO validation set and a proprietary dataset of industrial components, where we achieve substantial improvement on object detection accuracy. We also perform experiments on the automatic parameter tuning of Level Set models. Results show that our method facilitates considerable performance improvement on public datasets compared with baseline method. [ABSTRACT FROM AUTHOR]

Instance-wise contrastive learning (Instance-CL), which learns to map similar instances closer and different instances farther apart in the embedding space, has achieved considerable progress in self-supervised video representation learning. However, canonical Instance-CL does not handle properly the temporal similarities between different videos, limiting the representation capabilities of learned models. This paper presents a novel two-stage framework that combines Instance-CL and unsupervised clustering to progressively learn desirable temporal representations with high intra-class compactness. Specifically, (a) we first introduce a new consistency-preserving sampling strategy to generate positive/negative pairs. Compared to the traditional sampling methods, our sampling strategy focuses more on motion dynamics, resulting in more temporal-related feature representations. (b) To further explore the temporal similarities between videos so as to encourage intra-class compactness, we set temporal representations extracted from Instance-CL as an initializer, and iteratively use k-means clustering to generate pseudo-labels for training the encoder. We term our method as Improved Instance-CL with Deep Clustering (ICDC) and apply it to two downstream tasks, including action recognition and video retrieval. Extensive experimental results show that ICDC gains considerable improvements compared to the existing self-supervised methods. [ABSTRACT FROM AUTHOR]

Deep learning recognition approaches can potentially perform better if we can extract a discriminative representation that controllably separates nuisance factors. In this paper, we propose a novel approach to explicitly enforce the extracted discriminative representation $\boldsymbol{d}$ d , extracted latent variation $\boldsymbol{l}$ l (e,g., background, unlabeled nuisance attributes), and semantic variation label vector $\boldsymbol{s}$ s (e.g., labeled expressions/pose) to be independent and complementary to each other. We can cast this problem as an adversarial game in the latent space of an auto-encoder. Specifically, with the to-be-disentangled $\boldsymbol{s}$ s , we propose to equip an end-to-end conditional adversarial network with the ability to decompose an input sample into ${\boldsymbol{d}}$ d and $\boldsymbol{l}$ l . However, we argue that maximizing the cross-entropy loss of semantic variation prediction from $\boldsymbol{d}$ d is not sufficient to remove the impact of $\boldsymbol{s}$ s from $\boldsymbol{d}$ d , and that the uniform-target and entropy regularization are necessary. A collaborative mutual information regularization framework is further proposed to avoid unstable adversarial training. It is able to minimize the differentiable mutual information between the variables to enforce independence. The proposed discriminative representation inherits the desired tolerance property guided by prior knowledge of the task. Our proposed framework achieves top performance on diverse recognition tasks, including digits classification, large-scale face recognition on LFW and IJB-A datasets, and face recognition tolerant to changes in lighting, makeup, disguise, etc. [ABSTRACT FROM AUTHOR]

In this paper, we reveal that metric learning would suffer from serious inseparable problem if without informative sample mining. Since the inseparable samples are often mixed with hard samples, current informative sample mining strategies used to deal with inseparable problem may bring up some side-effects, such as instability of objective function, etc. To alleviate this problem, we propose a novel distance metric learning algorithm, named adaptive neighborhood metric learning (ANML). In ANML, we design two thresholds to adaptively identify the inseparable similar and dissimilar samples in the training procedure, thus inseparable sample removing and metric parameter learning are implemented in the same procedure. Due to the non-continuity of the proposed ANML, we develop an ingenious function, named log-exp mean function to construct a continuous formulation to surrogate it, which can be efficiently solved by the gradient descent method. Similar to Triplet loss, ANML can be used to learn both the linear and deep embeddings. By analyzing the proposed method, we find it has some interesting properties. For example, when ANML is used to learn the linear embedding, current famous metric learning algorithms such as the large margin nearest neighbor (LMNN) and neighbourhood components analysis (NCA) are the special cases of the proposed ANML by setting the parameters different values. When it is used to learn deep features, the state-of-the-art deep metric learning algorithms such as Triplet loss, Lifted structure loss, and Multi-similarity loss become the special cases of ANML. Furthermore, the log-exp mean function proposed in our method gives a new perspective to review the deep metric learning methods such as Prox-NCA and N-pairs loss. At last, promising experimental results demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

This paper generalizes the Attention in Attention (AiA) mechanism, in P. Fang et al., 2019 by employing explicit mapping in reproducing kernel Hilbert spaces to generate attention values of the input feature map. The AiA mechanism models the capacity of building inter-dependencies among the local and global features by the interaction of inner and outer attention modules. Besides a vanilla AiA module, termed linear attention with AiA, two non-linear counterparts, namely, second-order polynomial attention and Gaussian attention, are also proposed to utilize the non-linear properties of the input features explicitly, via the second-order polynomial kernel and Gaussian kernel approximation. The deep convolutional neural network, equipped with the proposed AiA blocks, is referred to as Attention in Attention Network (AiA-Net). The AiA-Net learns to extract a discriminative pedestrian representation, which combines complementary person appearance and corresponding part features. Extensive ablation studies verify the effectiveness of the AiA mechanism and the use of non-linear features hidden in the feature map for attention design. Furthermore, our approach outperforms current state-of-the-art by a considerable margin across a number of benchmarks. In addition, state-of-the-art performance is also achieved in the video person retrieval task with the assistance of the proposed AiA blocks. [ABSTRACT FROM AUTHOR]

Automatic liver tumor segmentation could offer assistance to radiologists in liver tumor diagnosis, and its performance has been significantly improved by recent deep learning based methods. These methods rely on large-scale well-annotated training datasets, but collecting such datasets is time-consuming and labor-intensive, which could hinder their performance in practical situations. Learning from synthetic data is an encouraging solution to address this problem. In our task, synthetic tumors can be injected to healthy images to form training pairs. However, directly applying the model trained using the synthetic tumor images on real test images performs poorly due to the domain shift problem. In this paper, we propose a novel approach, namely Synthetic-to-Real Test-Time Training (SR-TTT), to reduce the domain gap between synthetic training images and real test images. Specifically, we add a self-supervised auxiliary task, i.e., two-step reconstruction, which takes the output of the main segmentation task as its input to build an explicit connection between these two tasks. Moreover, we design a scheduled mixture strategy to avoid error accumulation and bias explosion in the training process. During test time, we adapt the segmentation model to each test image with self-supervision from the auxiliary task so as to improve the inference performance. The proposed method is extensively evaluated on two public datasets for liver tumor segmentation. The experimental results demonstrate that our proposed SR-TTT can effectively mitigate the synthetic-to-real domain shift problem in the liver tumor segmentation task, and is superior to existing state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (DCNNs) are currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning. The success of DCNNs can be attributed to the careful selection of their building blocks (e.g., residual blocks, rectifiers, sophisticated normalization schemes, to mention but a few). In this paper, we propose $\Pi$ Π -Nets, a new class of function approximators based on polynomial expansions. $\Pi$ Π -Nets are polynomial neural networks, i.e., the output is a high-order polynomial of the input. The unknown parameters, which are naturally represented by high-order tensors, are estimated through a collective tensor factorization with factors sharing. We introduce three tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks. We empirically demonstrate that $\Pi$ Π -Nets are very expressive and they even produce good results without the use of non-linear activation functions in a large battery of tasks and signals, i.e., images, graphs, and audio. When used in conjunction with activation functions, $\Pi$ Π -Nets produce state-of-the-art results in three challenging tasks, i.e., image generation, face verification and 3D mesh representation learning. The source code is available at https://github.com/grigorisg9gr/polynomial_nets. [ABSTRACT FROM AUTHOR]

Recent years have witnessed a big leap in automatic visual saliency detection attributed to advances in deep learning, especially Convolutional Neural Networks (CNNs). However, inferring the saliency of each image part separately, as was adopted by most CNNs methods, inevitably leads to an incomplete segmentation of the salient object. In this paper, we describe how to use the property of part-object relations endowed by the Capsule Network (CapsNet) to solve the problems that fundamentally hinge on relational inference for visual saliency detection. Concretely, we put in place a two-stream strategy, termed Two-Stream Part-Object RelaTional Network (TSPORTNet), to implement CapsNet, aiming to reduce both the network complexity and the possible redundancy during capsule routing. Additionally, taking into account the correlations of capsule types from the preceding training images, a correlation-aware capsule routing algorithm is developed for more accurate capsule assignments at the training stage, which also speeds up the training dramatically. By exploring part-object relationships, TSPORTNet produces a capsule wholeness map, which in turn aids multi-level features in generating the final saliency map. Experimental results on five widely-used benchmarks show that our framework consistently achieves state-of-the-art performance. The code can be found on https://github.com/liuyi1989/TSPORTNet. [ABSTRACT FROM AUTHOR]

Acoustic images are an emergent data modality for multimodal scene understanding. Such images have the peculiarity of distinguishing the spectral signature of the sound coming from different directions in space, thus providing a richer information as compared to that derived from single or binaural microphones. However, acoustic images are typically generated by cumbersome and costly microphone arrays which are not as widespread as ordinary microphones. This paper shows that it is still possible to generate acoustic images from off-the-shelf cameras equipped with only a single microphone and how they can be exploited for audio-visual scene understanding. We propose three architectures inspired by Variational Autoencoder, U-Net and adversarial models, and we assess their advantages and drawbacks. Such models are trained to generate spatialized audio by conditioning them to the associated video sequence and its corresponding monaural audio track. Our models are trained using the data collected by a microphone array as ground truth. Thus they learn to mimic the output of an array of microphones in the very same conditions. We assess the quality of the generated acoustic images considering standard generation metrics and different downstream tasks (classification, cross-modal retrieval and sound localization). We also evaluate our proposed models by considering multimodal datasets containing acoustic images, as well as datasets containing just monaural audio signals and RGB video frames. In all of the addressed downstream tasks we obtain notable performances using the generated acoustic data, when compared to the state of the art and to the results obtained using real acoustic images as input. [ABSTRACT FROM AUTHOR]

Visible-infrared person re-identification (VI-ReID) task aims to retrieve the same person between visible and infrared images. VI-ReID is challenging as the images captured by different spectra present large cross-modality discrepancy. Many methods adopt a two-stream network and design additional constraint conditions to extract shared features for different modalities. However, the interaction between the feature extraction processes of different modalities is rarely considered. In this paper, a partially interactive collaboration method is proposed to exploit the complementary information of different modalities to reduce the modality gap for VI-ReID. Specifically, the proposed method is achieved in a partially interactive-shared architecture: collaborative shallow layers and shared deep layers. The collaborative shallow layers consider the interaction between modality-specific features of different modalities, encouraging the feature extraction processes of different modalities constrain each other to enhance feature representations. The shared deep layers further embed the modality-specific features to a common space to endow them the same identity discriminability. To ensure the interactive collaborative learning implement effectively, the conventional loss and collaborative loss are utilized jointly to train the whole network. Extensive experiments on two publicly available VI-ReID datasets verify the superiority of the proposed PIC method. Specifically, the proposed method achieves a rank-1 accuracy of 83.6% and 57.5% on RegDB and SYSU-MM01 datasets, respectively. [ABSTRACT FROM AUTHOR]

High-precision road detection from very high resolution (VHR) remote sensing images has broad application value. However, the most advanced deep learning based methods often fail to identify roads when there is a distribution discrepancy between the training samples and test samples, due to their limited generalization ability. In this paper, to address this problem, an open-source data-driven domain-specific representation (OSM-DOER) framework is proposed for cross-domain road detection. On the one hand, as the spatial structure information of the source and target domains is similar, but the texture information is different, the domain-specific representation (DOER) framework is proposed, which not only aligns the distributions of the spatial structure information, but also learns the domain-specific texture information. Furthermore, in order to enhance the representation of the target domain data distribution, open-source and freely available OpenStreetMap (OSM) road centerline data are utilized to generate target domain samples, which are then used in the network training as the supervised information for the target domain. Finally, to verify the superiority of the proposed OSM-DOER framework, we conducted extensive experiments with the public SpaceNet and DeepGlobe road datasets, and large-scale road datasets from Birmingham in the UK and Shanghai in China. The experimental results demonstrate that the proposed OSM-DOER framework shows obvious advantages over the mainstream road detection methods, and the use of OSM road centerline data has great potential for the road detection task. [ABSTRACT FROM AUTHOR]

Due to the wavelength-dependent light attenuation, refraction and scattering, underwater images usually suffer from color distortion and blurred details. However, due to the limited number of paired underwater images with undistorted images as reference, training deep enhancement models for diverse degradation types is quite difficult. To boost the performance of data-driven approaches, it is essential to establish more effective learning mechanisms that mine richer supervised information from limited training sample resources. In this paper, we propose a novel underwater image enhancement network, called SGUIE-Net, in which we introduce semantic information as high-level guidance via region-wise enhancement feature learning. Accordingly, we propose semantic region-wise enhancement module to better learn local enhancement features for semantic regions with multi-scale perception. After using them as complementary features and feeding them to the main branch, which extracts the global enhancement features on the original image scale, the fused features bring semantically consistent and visually superior enhancements. Extensive experiments on the publicly available datasets and our proposed dataset demonstrate the impressive performance of SGUIE-Net. The code and proposed dataset are available at https://trentqq.github.io/SGUIE-Net.html . [ABSTRACT FROM AUTHOR]

Most existing RGB-D salient object detection (SOD) methods are primarily focusing on cross-modal and cross-level saliency fusion, which has been proved to be efficient and effective. However, these methods still have a critical limitation, i.e., their fusion patterns – typically the combination of selective characteristics and its variations, are too highly dependent on the network’s non-linear adaptability. In such methods, the balances between RGB and D (Depth) are formulated individually considering the intermediate feature slices, but the relation at the modality level may not be learned properly. The optimal RGB-D combinations differ depending on the RGB-D scenarios, and the exact complementary status is frequently determined by multiple modality-level factors, such as D quality, the complexity of the RGB scene, and degree of harmony between them. Therefore, given the existing approaches, it may be difficult for them to achieve further performance breakthroughs, as their methodologies belong to some methods that are somewhat less modality sensitive. To conquer this problem, this paper presents the Modality-aware Decoder (MaD). The critical technical innovations include a series of feature embedding, modality reasoning, and feature back-projecting and collecting strategies, all of which upgrade the widely-used multi-scale and multi-level decoding process to be modality-aware. Our MaD achieves competitive performance over other state-of-the-art (SOTA) models without using any fancy tricks in the decoder’s design. Codes and results will be publicly available at https://github.com/MengkeSong/MaD. [ABSTRACT FROM AUTHOR]

Recently, embedding and metric-based few-shot learning (FSL) has been introduced into hyperspectral image classification (HSIC) and achieved impressive progress. To further enhance the performance with few labeled samples, we in this paper propose a novel FSL framework for HSIC with a class-covariance metric (CMFSL). Overall, the CMFSL learns global class representations for each training episode by interactively using training samples from the base and novel classes, and a synthesis strategy is employed on the novel classes to avoid overfitting. During the meta-training and meta-testing, the class labels are determined directly using the Mahalanobis distance measurement rather than an extra classifier. Benefiting from the task-adapted class-covariance estimations, the CMFSL can construct more flexible decision boundaries than the commonly used Euclidean metric. Additionally, a lightweight cross-scale convolutional network (LXConvNet) consisting of 3D and 2D convolutions is designed to thoroughly exploit the spectral-spatial information in the high-frequency and low-frequency scales with low computational complexity. Furthermore, we devise a spectral-prior-based refinement module (SPRM) in the initial stage of feature extraction, which cannot only force the network to emphasize the most informative bands while suppressing the useless ones, but also alleviate the effects of the domain shift between the base and novel categories to learn a collaborative embedding mapping. Extensive experiment results on four benchmark data sets demonstrate that the proposed CMFSL can outperform the state-of-the-art methods with few-shot annotated samples. [ABSTRACT FROM AUTHOR]

Previous deep learning-based video stabilizers require a large scale of paired unstable and stable videos for training, which are difficult to collect. Traditional trajectory-based stabilizers, on the other hand, divide the task into several sub-tasks and tackle them subsequently, which are fragile in textureless and occluded regions regarding the usage of hand-crafted features. In this paper, we attempt to tackle the video stabilization problem in a deep unsupervised learning manner, which borrows the divide-and-conquer idea from traditional stabilizers while leveraging the representation power of DNNs to handle the challenges in real-world scenarios. Technically, DUT is composed of a trajectory estimation stage and a trajectory smoothing stage. In the trajectory estimation stage, we first estimate the motion of keypoints, initialize and refine the motion of grids via a novel multi-homography estimation strategy and a motion refinement network, respectively, and get the grid-based trajectories via temporal association. In the trajectory smoothing stage, we devise a novel network to predict dynamic smoothing kernels for trajectory smoothing, which can well adapt to trajectories with different dynamic patterns. We exploit the spatial and temporal coherence of keypoints and grid vertices to formulate the training objectives, resulting in an unsupervised training scheme. Experiment results on public benchmarks show that DUT outperforms state-of-the-art methods both qualitatively and quantitatively. The source code is available at https://github.com/Annbless/DUTCode. [ABSTRACT FROM AUTHOR]

Multi-focus image fusion (MFIF) attempts to achieve an “all-focused” image from multiple source images with the same scene but different focused objects. Given the lack of multi-focus image sets for network training, we propose a self-supervised residual feature learning model in this paper. The model consists of a feature extraction network and a fusion module. We select image super-resolution as a pretext task in the MFIF field, which is supported by a new residual gradient prior discovered by our theoretical study for low- and high-resolution (LR-HR) image pairs, as well as for multi-focus images. In the pretext task, our network’s training set is LR-HR image pairs generated from natural images, and HR images can be regarded as pseudo-labels of LR images. In the fusion task, the trained network extracts residual features of multi-focus images firstly. Secondly, the fusion module, consisting of an activity level measurement and a new boundary refinement method, is leveraged for the features to generated decision maps. Experimental results, both subjective evaluations and objective evaluations, demonstrate that our approach outperforms other state-of-the-art fusion algorithms. [ABSTRACT FROM AUTHOR]

We consider the problem of obtaining image quality representations in a self-supervised manner. We use prediction of distortion type and degree as an auxiliary task to learn features from an unlabeled image dataset containing a mixture of synthetic and realistic distortions. We then train a deep Convolutional Neural Network (CNN) using a contrastive pairwise objective to solve the auxiliary problem. We refer to the proposed training framework and resulting deep IQA model as the CONTRastive Image QUality Evaluator (CONTRIQUE). During evaluation, the CNN weights are frozen and a linear regressor maps the learned representations to quality scores in a No-Reference (NR) setting. We show through extensive experiments that CONTRIQUE achieves competitive performance when compared to state-of-the-art NR image quality models, even without any additional fine-tuning of the CNN backbone. The learned representations are highly robust and generalize well across images afflicted by either synthetic or authentic distortions. Our results suggest that powerful quality representations with perceptual relevance can be obtained without requiring large labeled subjective image quality datasets. The implementations used in this paper are available at https://github.com/pavancm/CONTRIQUE. [ABSTRACT FROM AUTHOR]

The difficulties of obtaining sufficient labeled samples have always been one of the factors hindering deep learning models from obtaining high accuracy in hyperspectral image (HSI) classification. To reduce the dependence of deep learning models on training samples, meta learning methods have been introduced, effectively improving the classification accuracy in small sample set scenarios. However, the existing methods based on meta learning still need to construct a labeled source data set with several pre-collected HSIs, and must utilize a large number of labeled samples for meta-training, which is actually time-consuming and labor-intensive. To solve this problem, this paper proposes a novel unsupervised meta learning method with multiview constraints for HSI small sample set classification. Specifically, the proposed method first builds an unlabeled source data set using unlabeled HSIs. Then, multiple spatial-spectral multiview features of each unlabeled sample are generated to construct tasks for unsupervised meta learning. Finally, the designed residual relation network is used for meta-training and small sample set classification based on the voting strategy. Compared with existing supervised meta learning methods for HSI classification, our method can only utilize HSIs without any label for unsupervised meta learning, which significantly reduces the number of requisite labeled samples in the whole classification process. To verify the effectiveness of the proposed method, extensive experiments are carried out on 8 public HSIs in the cross-domain and in-domain classification scenarios. The statistical results demonstrate that, compared with existing supervised meta learning methods and other advanced classification models, the proposed method can achieve competitive or better classification performance in small sample set scenarios. [ABSTRACT FROM AUTHOR]

The practical task of Automatic Check-Out (ACO) is to accurately predict the presence and count of each product in an arbitrary product combination. Beyond the large-scale and the fine-grained nature of product categories as its main challenges, products are always continuously updated in realistic check-out scenarios, which is also required to be solved in an ACO system. Previous work in this research line almost depends on the supervisions of labor-intensive bounding boxes of products by performing a detection paradigm. While, in this paper, we propose a Self-Supervised Multi-Category Counting (S2MC2) network to leverage the point-level supervisions of products in check-out images to both lower the labeling cost and be able to return ACO predictions in a class incremental setting. Specifically, as a backbone, our S2MC2 is built upon a counting module in a class-agnostic counting fashion. Also, it consists of several crucial components including an attention module for capturing fine-grained patterns and a domain adaptation module for reducing the domain gap between single product images as training and check-out images as test. Furthermore, a self-supervised approach is utilized in S2MC2 to initialize the parameters of its backbone for better performance. By conducting comprehensive experiments on the large-scale automatic check-out dataset RPC, we demonstrate that our proposed S2MC2 achieves superior accuracy in both traditional and incremental settings of ACO tasks over the competing baselines. [ABSTRACT FROM AUTHOR]

Unsupervised active learning has become an active research topic in the machine learning and computer vision communities, whose goal is to choose a subset of representative samples to be labeled in an unsupervised setting. Most of existing approaches rely on shallow linear models by assuming that each sample can be well approximated by the span (i.e., the set of all linear combinations) of the selected samples, and then take these selected samples as the representative ones for manual labeling. However, the data do not necessarily conform to the linear models in many real-world scenarios, and how to model nonlinearity of data often becomes the key point of unsupervised active learning. Moreover, the existing works often aim to well reconstruct the whole dataset, while ignore the important cluster structure, especially for imbalanced data. In this paper, we present a novel deep unsupervised active learning framework. The proposed method can explicitly learn a nonlinear embedding to map each input into a latent space via a deep neural network, and introduce a selection block to select the representative samples in the learnt latent space through a self-supervised learning strategy. In the selection block, we aim to not only preserve the global structure of the data, but also capture the cluster structure of the data in order to well handle the data imbalance issue during sample selection. Meanwhile, we take advantage of the clustering result to provide self-supervised information to guide the above processes. Finally, we attempt to preserve the local structure of the data, such that the data embedding becomes more precise and the model performance can be further improved. Extensive experimental results on several publicly available datasets clearly demonstrate the effectiveness of our method, compared with the state-of-the-arts. [ABSTRACT FROM AUTHOR]

Deep object detection models trained on clean images may not generalize well on degraded images due to the well-known domain shift issue. This hinders their application in real-life scenarios such as video surveillance and autonomous driving. Though domain adaptation methods can adapt the detection model from a labeled source domain to an unlabeled target domain, they struggle in dealing with open and compound degradation types. In this paper, we attempt to address this problem in the context of object detection by proposing a robust object Detector via Adversarial Novel Style Exploration (DANSE). Technically, DANSE first disentangles images into domain-irrelevant content representation and domain-specific style representation under an adversarial learning framework. Then, it explores the style space to discover diverse novel degradation styles that are complementary to those of the target domain images by leveraging a novelty regularizer and a diversity regularizer. The clean source domain images are transferred into these discovered styles by using a content-preserving regularizer to ensure realism. These transferred source domain images are combined with the target domain images and used to train a robust degradation-agnostic object detection model via adversarial domain adaptation. Experiments on both synthetic and real benchmark scenarios confirm the superiority of DANSE over state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Different from the object motion blur, the defocus blur is caused by the limitation of the cameras’ depth of field. The defocus amount can be characterized by the parameter of point spread function and thus forms a defocus map. In this paper, we propose a new network architecture called Defocus Image Deblurring Auxiliary Learning Net (DID-ANet), which is specifically designed for single image defocus deblurring by using defocus map estimation as auxiliary task to improve the deblurring result. To facilitate the training of the network, we build a novel and large-scale dataset for single image defocus deblurring, which contains the defocus images, the defocus maps and the all-sharp images. To the best of our knowledge, the new dataset is the first large-scale defocus deblurring dataset for training deep networks. Moreover, the experimental results demonstrate that the proposed DID-ANet outperforms the state-of-the-art methods for both tasks of defocus image deblurring and defocus map estimation, both quantitatively and qualitatively. The dataset, code, and model is available on GitHub: https://github.com/xytmhy/DID-ANet-Defocus-Deblurring. [ABSTRACT FROM AUTHOR]

Face aging aims to estimate aged facial textures given a certain face image. A number of 2D face-aging methods have been developed, but there have been few studies on 3D face aging, which would be valuable in several real-world applications. The lack of 3D face-aging data has had a significant impact on the development of 3D face aging, but we hypothesized that the large amounts of 2D face-aging data on the internet could be leveraged for 3D aged facial textures. In this paper, we propose a novel 3D aging framework, which we call UV-transformation texture estimation based on generative adversarial networks (UVTE-GAN), to achieve 3D face aging. Specifically, the proposed framework has three parts: 1) a 3D vertex and texture estimator, which accurately estimates the face’s spatial vertices and textures; 2) a texture-aging GAN, which is responsible for aging the estimated texture map via adversarial learning; and 3) a 2D & 3D rendering rebuilder, which recovers 2D & 3D faces using the estimated facial vertex map and aged facial texture map. In addition, we also design a plugin layer that allows us to train the whole model in an end-to-end manner. Experimental results demonstrate the effectiveness of the proposed method in synthesizing visually pleasing 3D aged face pictures, and state-of-the-art performance is achieved on several public datasets. [ABSTRACT FROM AUTHOR]

Background matting is a recently developed image matting approach, with applications to image and video editing. It refers to estimating both the alpha matte and foreground from a pair of images with and without foreground objects. Recent work has applied deep learning to background matting, with very promising performance achieved. However, existing deep models are supervised which require a large dataset with ground truth alpha mattes for training. To avoid the cost of data collection and possible bias in training data, this paper proposes a dataset-free unsupervised deep learning-based approach for background matting. Observing that the local smoothness of alpha matte can be well characterized by the untrained network prior called deep matte prior, we model the foreground and alpha matte using the priors encoded by two generative convolutional neural networks. To avoid possible overfitting during unsupervised learning, a two-stage learning scheme is developed which contains projection-based training and Bayesian post refinement. An alpha-matte-driven initialization scheme is also developed for performance boost. Even without calling external training data, the proposed approach provides competitive performance to recent supervised learning-based methods in the experiments. [ABSTRACT FROM AUTHOR]

In the Few-Shot Learning (FSL), much of the related efforts only rely on the few available labeled samples (support set) building approach. However, the challenge is that the support set is easy-to-be-biased, so that they cannot be competent prototypes and are hard to represent the class distribution, leading to performance bottlenecks. In this paper, we propose to solve this obstacle by capturing the distribution of the unlabeled samples (query set). We propose two sampling methods: DeepSearch ($\cal DS$) and WideSearch ($\cal WS$). Both approaches are simple to implement and have no trainable parameters. They search the query samples near to the support set in different manners. Afterward, the statistic information is calculated, and we generate the latent samples according to it. The generated latent set is promising. First, it brings the query set distribution information to the classifier, which significantly improves the performance of the cross-entropy-based classifier. Second, it helps the support set become the better prototypes, which boosts the performance of the prototype-based classifier. Third, we find few latent samples are enough to boost the performance. Abundant experiments prove the proposed method achieves state-of-the-art performance on the few-shot tasks. Finally, rich ablation studies explain the compelling details of our approach. [ABSTRACT FROM AUTHOR]

Edge-preserving image filtering is an essential task in computational photography and imaging. In this paper, we propose a simple yet effective global edge-preserving filter based on soft clustering, and we propose a novel soft clustering algorithm based on a restricted Gaussian mixture model. Given specified parameters, the soft clustering process is firstly performed on the image to derive the partition matrix, from which the affinity matrix is then constructed for filtering. The filtering output is calculated as the weighted average of the pixels in the local window, so the proposed filter could suppress the intensity shift artifacts that impede most global filters. Besides, the weights in the proposed filter are derived by clustering, which properly separates dissimilar pixels, so the proposed filter could handle the halo artifacts that haunt many local filters. Moreover, our filter provides flexible control over the amount of smoothing that is deficient in the deep learning-based filters. Besides the efficacy in smoothing, the proposed filter naturally has low computational complexity. Qualitative and quantitative results suggest that the proposed filter benefits various applications, including edge-preserving smoothing, image enhancing, flash/non-flash fusion, HDR tone mapping, and dehazing. [ABSTRACT FROM AUTHOR]

The core purpose of deep metric learning is to construct an embedding space, where objects belonging to the same class are gathered together and the ones from different classes are pushed apart. Most existing approaches typically insist to inter-class characteristics, e.g., class-level information or instance-level similarity, to obtain semantic relevance of data points and get a large margin between different classes in the embedding space. However, the intra-class characteristics, e.g., local manifold structure or relative relationship within the same class, are usually overlooked in the learning process. Hence the output embeddings have limitation in retrieving a good ranking result if existing multiple positive samples. And the local data structure of embedding space cannot be fully exploited since lack of relative ranking information. As a result, the model is prone to overfitting on a train set and get low generalization on the test set (unseen classes) when losing sight of intra-class variance. This paper presents a novel self-supervised synthesis ranking auxiliary framework, which captures intra-class characteristics as well as inter-class characteristics for better metric learning. Our method designs a synthetic samples generation of polar coordinates to generate measurable intra-class variance with different strength and diversity in the latent space, which can simulate the various local structure change of intra-class in the initial data domain. And then formulates a self-supervised learning procedure to fully exploit this property and preserve it in the embedding space. As a result, the learned embedding space not only keeps inter-class discrimination but also owns subtle intra-class diversity, leading to better global and local embedding structures. Extensive experiments on five benchmarks show that our method significantly improves and outperforms the state-of-the-art methods on the performances of both retrieval and ranking by 2%-4% (personal use of this material is permitted. However, permission to use this material for any other purposes must be obtained from the IEEE by sending an email to pubs-permissions@ieee.org). [ABSTRACT FROM AUTHOR]

This paper considers deep visual recognition on long-tailed data. Under the long-tailed distribution, a small portion of the classes (head classes) occupy most training samples and the most classes (tail classes) only occupy relatively few samples. We observe that such long-tailed distribution significantly distorts the deeply-learned feature space, which consequentially compromises the deep visual recognition. Specifically, during training, each head class is prone to a relatively wide spatial distribution in the deep feature space, while each tail class is prone to a relatively small spatial distribution. In another word, the tail classes usually have much smaller spatial distribution than the head classes, distorting the overall feature space. In response, we propose to explicitly inflate the distribution of each tail class in the deep feature space, so that the tail classes will have comparable distribution range as the head classes. To this end, we replace each tail feature vector with a set of feature vectors on the fly. These feature vectors follow a probabilistic distribution learned from the head classes and yield a “feature cloud” surrounding the original tail feature. We show that the feature cloud effectively transfers the within-class diversity from the head classes onto the tail classes, maintaining an effect of probabilistic feature augmentation. An important advantage of the proposed feature cloud is that it is capable to bring general improvement to long-tailed visual recognition on two fundamental tasks, i.e., deep classification and deep representation learning, in spite of the significant differences between them. Extensive experiments on both deep metric learning benchmarks and deep image classification benchmarks validate the effectiveness of the proposed feature cloud. [ABSTRACT FROM AUTHOR]

Undersampling the k-space during MR acquisitions saves time, however results in an ill-posed inversion problem, leading to an infinite set of images as possible solutions. Traditionally, this is tackled as a reconstruction problem by searching for a single “best” image out of this solution set according to some chosen regularization or prior. This approach, however, misses the possibility of other solutions and hence ignores the uncertainty in the inversion process. In this paper, we propose a method that instead returns multiple images which are possible under the acquisition model and the chosen prior to capture the uncertainty in the inversion process. To this end, we introduce a low dimensional latent space and model the posterior distribution of the latent vectors given the acquisition data in k-space, from which we can sample in the latent space and obtain the corresponding images. We use a variational autoencoder for the latent model and the Metropolis adjusted Langevin algorithm for the sampling. We evaluate our method on two datasets; with images from the Human Connectome Project and in-house measured multi-coil images. We compare to five alternative methods. Results indicate that the proposed method produces images that match the measured k-space data better than the alternatives, while showing realistic structural variability. Furthermore, in contrast to the compared methods, the proposed method yields higher uncertainty in the undersampled phase encoding direction, as expected. [ABSTRACT FROM AUTHOR]

The ability to predict, anticipate and reason about future outcomes is a key component of intelligent decision-making systems. In light of the success of deep learning in computer vision, deep-learning-based video prediction emerged as a promising research direction. Defined as a self-supervised learning task, video prediction represents a suitable framework for representation learning, as it demonstrated potential capabilities for extracting meaningful representations of the underlying patterns in natural videos. Motivated by the increasing interest in this task, we provide a review on the deep learning methods for prediction in video sequences. We first define the video prediction fundamentals, as well as mandatory background concepts and the most used datasets. Next, we carefully analyze existing video prediction models organized according to a proposed taxonomy, highlighting their contributions and their significance in the field. The summary of the datasets and methods is accompanied with experimental results that facilitate the assessment of the state of the art on a quantitative basis. The paper is summarized by drawing some general conclusions, identifying open research challenges and by pointing out future research directions. [ABSTRACT FROM AUTHOR]

Infrared image retains typical thermal targets while visible image preserves rich texture details, image fusion aims to reconstruct a synthesized image containing prominent targets and abundant texture details. Most of deep learning-based methods mainly focus on convolution operation to extract the local features, but do not fully consider their multi-scale characteristics and global dependencies, which may cause loss of target regions and texture details in the fused image. Towards this goal, we present a unified multi-scale densely connected fusion network in this paper, named as UNFusion. We carefully design a multi-scale encoder-decoder architecture that can efficiently extract and reconstruct multi-scale deep features. Dense skip connections are employed in both encoder and decoder sub-networks to reuse all the intermediate features of different layers and scales for fusion tasks. In the fusion layer, $L_{p} $ normalized attention models, which include three kinds of different norms, are proposed to highlight and combine these deep features from spatial and channel dimensions, and the combined spatial and channel attention maps are used to reconstruct a final fused image. We conduct extensive experiments on the public TNO and Roadscene datasets, and the results demonstrate that our UNFusion can simultaneously preserve high brightness of typical thermal targets and abundant texture details to obtain superior scene representation and better visual perception. Besides, our UNFusion achieves better fusion performance and transcends other state-of-the-art methods in terms of qualitative and quantitative comparisons. Our code is available at https://github.com/Zhishe-Wang/UNFusion. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a novel point-to-surface representation for 3D point cloud learning. Unlike the previous methods that mainly adopt voxel, mesh, or point coordinates, we propose to tackle this problem from a new perspective: learn a set of quadratic terms based static and global reference surfaces to describe 3D shapes, such that the coordinates of a 3D point (x, y, z) can be extended to quadratic terms (xy, xz, yz, $\ldots $) and transformed to the relationship between the local point and the global reference surfaces. Then, the static surfaces are changed into dynamic surfaces by adaptive contribution weighting to improve the descriptive capability. Towards this end, we propose our point-to-surface representation, a new representation for 3D point cloud learning that has not been attempted before, which can assemble local and global geometric information effectively by building connections between the point cloud and the learned reference surfaces. Given 3D points, we show how the reference surfaces are constructed, and how they are inserted into the 3D learning pipeline for different tasks. The experimental results confirm the effectiveness of our new representation, which has outperformed the state-of-the-art methods on the tasks of 3D classification and segmentation. [ABSTRACT FROM AUTHOR]

Deep convolutional neural network (DCNN) models have been widely explored for skin disease diagnosis and some of them have achieved the diagnostic outcomes comparable or even superior to those of dermatologists. However, broad implementation of DCNN in skin disease detection is hindered by small size and data imbalance of the publically accessible skin lesion datasets. This paper proposes a novel single-model based strategy for classification of skin lesions on small and imbalanced datasets. First, various DCNNs are trained on different small and imbalanced datasets to verify that the models with moderate complexity outperform the larger models. Second, regularization DropOut and DropBlock are added to reduce overfitting and a Modified RandAugment augmentation strategy is proposed to deal with the defects of sample underrepresentation in the small dataset. Finally, a novel Multi-Weighted New Loss (MWNL) function and an end-to-end cumulative learning strategy (CLS) are introduced to overcome the challenge of uneven sample size and classification difficulty and to reduce the impact of abnormal samples on training. By combining Modified RandAugment, MWNL and CLS, our single DCNN model method achieved the classification accuracy comparable or superior to those of multiple ensembling models on different dermoscopic image datasets. Our study shows that this method is able to achieve a high classification performance at a low cost of computational resources and inference time, potentially suitable to implement in mobile devices for automated screening of skin lesions and many other malignancies in low resource settings. [ABSTRACT FROM AUTHOR]

Deep neural networks, in particular convolutional networks, have rapidly become a popular choice for analyzing histopathology images. However, training these models relies heavily on a large number of samples manually annotated by experts, which is cumbersome and expensive. In addition, it is difficult to obtain a perfect set of labels due to the variability between expert annotations. This paper presents a novel active learning (AL) framework for histopathology image analysis, named PathAL. To reduce the required number of expert annotations, PathAL selects two groups of unlabeled data in each training iteration: one “informative” sample that requires additional expert annotation, and one “confident predictive” sample that is automatically added to the training set using the model’s pseudo-labels. To reduce the impact of the noisy-labeled samples in the training set, PathAL systematically identifies noisy samples and excludes them to improve the generalization of the model. Our model advances the existing AL method for medical image analysis in two ways. First, we present a selection strategy to improve classification performance with fewer manual annotations. Unlike traditional methods focusing only on finding the most uncertain samples with low prediction confidence, we discover a large number of high confidence samples from the unlabeled set and automatically add them for training with assigned pseudo-labels. Second, we design a method to distinguish between noisy samples and hard samples using a heuristic approach. We exclude the noisy samples while preserving the hard samples to improve model performance. Extensive experiments demonstrate that our proposed PathAL framework achieves promising results on a prostate cancer Gleason grading task, obtaining similar performance with 40% fewer annotations compared to the fully supervised learning scenario. An ablation study is provided to analyze the effectiveness of each component in PathAL, and a pathologist reader study is conducted to validate our proposed algorithm. [ABSTRACT FROM AUTHOR]

Usually considered as a classification problem, entity resolution (ER) can be very challenging on real data due to the prevalence of dirty values. The state-of-the-art solutions for ER were built on a variety of learning models (most notably deep neural networks), which require lots of accurately labeled training data. Unfortunately, high-quality labeled data usually require expensive manual work, and are therefore not readily available in many real scenarios. In this paper, we propose a novel learning paradigm for ER, called gradual machine learning, which aims to enable effective machine labeling without the requirement for manual labeling effort. It begins with some easy instances in a task, which can be automatically labeled by the machine with high accuracy, and then gradually labels more challenging instances by iterative factor graph inference. In gradual machine learning, the hard instances in a task are gradually labeled in small stages based on the estimated evidential certainty provided by the labeled easier instances. Our extensive experiments on real data have shown that the performance of the proposed approach is considerably better than its unsupervised alternatives, and highly competitive compared to the state-of-the-art supervised techniques. Using ER as a test case, we demonstrate that gradual machine learning is a promising paradigm potentially applicable to other challenging classification tasks requiring extensive labeling effort. [ABSTRACT FROM AUTHOR]

To overcome the absence of concrete supervisory signals, deep clustering models construct their own labels based on self-supervision and pseudo-supervision. However, applying these techniques can cause Feature Randomness and Feature Drift. In this paper, we formally characterize these two new concepts. On one hand, Feature Randomness takes place when a considerable portion of the pseudo-labels is deemed to be random. In this regard, the trained model can learn non-representative features. On the other hand, Feature Drift takes place when the pseudo-supervised and the reconstruction losses are jointly minimized. While penalizing the reconstruction loss aims to preserve all the inherent data information, optimizing the embedded-clustering objective drops the latent between-cluster variances. Due to this compromise, the clustering-friendly representations can be easily drifted. In this context, we propose ADEC (Adversarial Deep Embedded Clustering) a novel autoencoder-based clustering model, which relies on a discriminator network to reduce random features while avoiding the drifting effect. Our new metrics $\Delta _{FR}$ Δ F R and $\Delta _{FD}$ Δ F D allows to, respectively, assess the level of Feature Randomness and Feature Drift. We empirically demonstrate the suitability of our model on handling these problems using benchmark real datasets. Experimental results validate that our model outperforms state-of-the-art autoencoder-based clustering methods. [ABSTRACT FROM AUTHOR]

Deep learning is increasingly popular, partly due to its widespread application potential, such as in civilian, government and military domains. Given the exacting computational requirements, cloud computing has been utilized to host user data and model. However, such an approach has potential privacy implications. Therefore, in this paper, we propose a method to protect user’s privacy in the inference phase of deep learning workflow. Specifically, we use an intermediate layer to separate the entire neural network into two parts, which are respectively deployed on the user device and the cloud server. The encoder, deployed on the user device, is used for raw data transformation, which removes the need for users to upload raw data to the cloud directly. However, we also demonstrate there exists potential for privacy leakage in the intermediate features of the neural network through two concrete experiments. In other words, the encoder on its own does not provide adequate privacy protection. Therefore, we also propose an approach to achieve Privacy-preserving Feature Extraction based on Adversarial Training (P-FEAT), where the goal of privacy attacking tasks and the goal of target tasks are adversarial in terms of sensitive attributes. By imposing privacy constraints during the feature extraction, we can reduce the contribution of the extracted features to the privacy leakage. In this way, privacy protection capability of the encoder can be further strengthened. We then demonstrate the effectiveness of P-FEAT using a large number of experiments, whose findings show that P-FEAT can significantly reduce the threats of privacy attacking tasks while maintaining high accuracy of the target tasks. [ABSTRACT FROM AUTHOR]

This paper presents U-LanD, a framework for automatic detection of landmarks on key frames of the video by leveraging the uncertainty of landmark prediction. We tackle a specifically challenging problem, where training labels are noisy and highly sparse. U-LanD builds upon a pivotal observation: a deep Bayesian landmark detector solely trained on key video frames, has significantly lower predictive uncertainty on those frames vs. other frames in videos. We use this observation as an unsupervised signal to automatically recognize key frames on which we detect landmarks. As a test-bed for our framework, we use ultrasound imaging videos of the heart, where sparse and noisy clinical labels are only available for a single frame in each video. Using data from 4,493 patients, we demonstrate that U-LanD can exceedingly outperform the state-of-the-art non-Bayesian counterpart by a noticeable absolute margin of 42% in ${R}^{{2}}$ score, with almost no overhead imposed on the model size. [ABSTRACT FROM AUTHOR]