Search

In dyadic interaction, predicting the listener's facial reactions is challenging as different reactions may be appropriate in response to the same speaker's behaviour. This paper presents a novel framework called ReactFace that learns an appropriate facial reaction distribution from a speaker's behaviour rather than replicating the real facial reaction of the listener. ReactFace generates multiple different but appropriate photo-realistic human facial reactions by (i) learning an appropriate facial reaction distribution representing multiple appropriate facial reactions; and (ii) synchronizing the generated facial reactions with the speaker's verbal and non-verbal behaviours at each time stamp, resulting in realistic 2D facial reaction sequences. Experimental results demonstrate the effectiveness of our approach in generating multiple diverse, synchronized, and appropriate facial reactions from each speaker's behaviour, with the quality of the generated reactions being influenced by the speaker's speech and facial behaviours. Our code is made publicly available at \url{https://github.com/lingjivoo/ReactFace}., 10 pages, 6 figures

Various stuff and things in visual data possess specific traits, which can be learned by deep neural networks and are implicitly represented as the visual prior, e.g., object location and shape, in the model. Such prior potentially impacts many vision tasks. For example, in conditional image synthesis, spatial conditions failing to adhere to the prior can result in visually inaccurate synthetic results. This work aims to explicitly learn the visual prior and enable the customization of sampling. Inspired by advances in language modeling, we propose to learn Visual prior via Generative Pre-Training, dubbed VisorGPT. By discretizing visual locations of objects, e.g., bounding boxes, human pose, and instance masks, into sequences, VisorGPT can model visual prior through likelihood maximization. Besides, prompt engineering is investigated to unify various visual locations and enable customized sampling of sequential outputs from the learned prior. Experimental results demonstrate that VisorGPT can effectively model the visual prior, which can be employed for many vision tasks, such as customizing accurate human pose for conditional image synthesis models like ControlNet. Code will be released at https://github.com/Sierkinhane/VisorGPT., Project web-page: https://sierkinhane.github.io/visor-gpt/

In implant prosthesis treatment, the design of surgical guide requires lots of manual labors and is prone to subjective variations. When deep learning based methods has started to be applied to address this problem, the space between teeth are various and some of them might present similar texture characteristic with the actual implant region. Both problems make a big challenge for the implant position prediction. In this paper, we develop a two-stream implant position regression framework (TSIPR), which consists of an implant region detector (IRD) and a multi-scale patch embedding regression network (MSPENet), to address this issue. For the training of IRD, we extend the original annotation to provide additional supervisory information, which contains much more rich characteristic and do not introduce extra labeling costs. A multi-scale patch embedding module is designed for the MSPENet to adaptively extract features from the images with various tooth spacing. The global-local feature interaction block is designed to build the encoder of MSPENet, which combines the transformer and convolution for enriched feature representation. During inference, the RoI mask extracted from the IRD is used to refine the prediction results of the MSPENet. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed TSIPR achieves superior performance than existing methods.

When deep neural network has been proposed to assist the dentist in designing the location of dental implant, most of them are targeting simple cases where only one missing tooth is available. As a result, literature works do not work well when there are multiple missing teeth and easily generate false predictions when the teeth are sparsely distributed. In this paper, we are trying to integrate a weak supervision text, the target region, to the implant position regression network, to address above issues. We propose a text condition embedded implant position regression network (TCEIP), to embed the text condition into the encoder-decoder framework for improvement of the regression performance. A cross-modal interaction that consists of cross-modal attention (CMA) and knowledge alignment module (KAM) is proposed to facilitate the interaction between features of images and texts. The CMA module performs a cross-attention between the image feature and the text condition, and the KAM mitigates the knowledge gap between the image feature and the image encoder of the CLIP. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed TCEIP achieves superior performance than existing methods., Comment: MICCAI 2023

Verbal and non-verbal human reaction generation is a challenging task, as different reactions could be appropriate for responding to the same behaviour. This paper proposes the first multiple and multimodal (verbal and nonverbal) appropriate human reaction generation framework that can generate appropriate and realistic human-style reactions (displayed in the form of synchronised text, audio and video streams) in response to an input user behaviour. This novel technique can be applied to various human-computer interaction scenarios by generating appropriate virtual agent/robot behaviours. Our demo is available at \url{https://github.com/SSYSteve/MRecGen}.

In this study, we examine the associations between channel features and convolutional kernels during the processes of feature purification and gradient backpropagation, with a focus on the forward and backward propagation within the network. Consequently, we propose a method called Dense Channel Compression for Feature Spatial Solidification. Drawing upon the central concept of this method, we introduce two innovative modules for backbone and head networks: the Dense Channel Compression for Feature Spatial Solidification Structure (DCFS) and the Asymmetric Multi-Level Compression Decoupled Head (ADH). When integrated into the YOLOv5 model, these two modules demonstrate exceptional performance, resulting in a modified model referred to as YOLOCS. Evaluated on the MSCOCO dataset, the large, medium, and small YOLOCS models yield AP of 50.1%, 47.6%, and 42.5%, respectively. Maintaining inference speeds remarkably similar to those of the YOLOv5 model, the large, medium, and small YOLOCS models surpass the YOLOv5 model's AP by 1.1%, 2.3%, and 5.2%, respectively.

This paper presents our Facial Action Units (AUs) detection submission to the fifth Affective Behavior Analysis in-the-wild Competition (ABAW). Our approach consists of three main modules: (i) a pre-trained facial representation encoder which produce a strong facial representation from each input face image in the input sequence; (ii) an AU-specific feature generator that specifically learns a set of AU features from each facial representation; and (iii) a spatio-temporal graph learning module that constructs a spatio-temporal graph representation. This graph representation describes AUs contained in all frames and predicts the occurrence of each AU based on both the modeled spatial information within the corresponding face and the learned temporal dynamics among frames. The experimental results show that our approach outperformed the baseline and the spatio-temporal graph representation learning allows our model to generate the best results among all ablated systems. Our model ranks at the 4th place in the AU recognition track at the 5th ABAW Competition. Our code is publicly available at https://github.com/wzh125/ABAW-5.

While remarkable success has been achieved in weakly-supervised object localization (WSOL), current frameworks are not capable of locating objects of novel categories in open-world settings. To address this issue, we are the first to introduce a new weakly-supervised object localization task called OWSOL (Open-World Weakly-Supervised Object Localization). During training, all labeled data comes from known categories and, both known and novel categories exist in the unlabeled data. To handle such data, we propose a novel paradigm of contrastive representation co-learning using both labeled and unlabeled data to generate a complete G-CAM (Generalized Class Activation Map) for object localization, without the requirement of bounding box annotation. As no class label is available for the unlabelled data, we conduct clustering over the full training set and design a novel multiple semantic centroids-driven contrastive loss for representation learning. We re-organize two widely used datasets, i.e., ImageNet-1K and iNatLoc500, and propose OpenImages150 to serve as evaluation benchmarks for OWSOL. Extensive experiments demonstrate that the proposed method can surpass all baselines by a large margin. We believe that this work can shift the close-set localization towards the open-world setting and serve as a foundation for subsequent works. Code will be released at https://github.com/ryylcc/OWSOL.

In this paper, we propose a novel 3D graph convolution based pipeline for category-level 6D pose and size estimation from monocular RGB-D images. The proposed method leverages an efficient 3D data augmentation and a novel vector-based decoupled rotation representation. Specifically, we first design an orientation-aware autoencoder with 3D graph convolution for latent feature learning. The learned latent feature is insensitive to point shift and size thanks to the shift and scale-invariance properties of the 3D graph convolution. Then, to efficiently decode the rotation information from the latent feature, we design a novel flexible vector-based decomposable rotation representation that employs two decoders to complementarily access the rotation information. The proposed rotation representation has two major advantages: 1) decoupled characteristic that makes the rotation estimation easier; 2) flexible length and rotated angle of the vectors allow us to find a more suitable vector representation for specific pose estimation task. Finally, we propose a 3D deformation mechanism to increase the generalization ability of the pipeline. Extensive experiments show that the proposed pipeline achieves state-of-the-art performance on category-level tasks. Further, the experiments demonstrate that the proposed rotation representation is more suitable for the pose estimation tasks than other rotation representations., revised from CVPR2021 paper FS-NET. arXiv admin note: substantial text overlap with arXiv:2103.07054

Recent mainstream weakly-supervised semantic segmentation (WSSS) approaches mainly relies on image-level classification learning, which has limited representation capacity. In this paper, we propose a novel semantic learning based framework, named SLAMs (Semantic Learning based Activation Map), for WSSS.

Scientific literature serves as a high-quality corpus, supporting a lot of Natural Language Processing (NLP) research. However, existing datasets are centered around the English language, which restricts the development of Chinese scientific NLP. In this work, we present CSL, a large-scale Chinese Scientific Literature dataset, which contains the titles, abstracts, keywords and academic fields of 396k papers. To our knowledge, CSL is the first scientific document dataset in Chinese. The CSL can serve as a Chinese corpus. Also, this semi-structured data is a natural annotation that can constitute many supervised NLP tasks. Based on CSL, we present a benchmark to evaluate the performance of models across scientific domain tasks, i.e., summarization, keyword generation and text classification. We analyze the behavior of existing text-to-text models on the evaluation tasks and reveal the challenges for Chinese scientific NLP tasks, which provides a valuable reference for future research. Data and code are available at https://github.com/ydli-ai/CSL, to be published in COLING 2022

Accurate abnormality localization in chest X-rays (CXR) can benefit the clinical diagnosis of various thoracic diseases. However, the lesion-level annotation can only be performed by experienced radiologists, and it is tedious and time-consuming, thus difficult to acquire. Such a situation results in a difficulty to develop a fully-supervised abnormality localization system for CXR. In this regard, we propose to train the CXR abnormality localization framework via a weakly semi-supervised strategy, termed Point Beyond Class (PBC), which utilizes a small number of fully annotated CXRs with lesion-level bounding boxes and extensive weakly annotated samples by points. Such a point annotation setting can provide weakly instance-level information for abnormality localization with a marginal annotation cost. Particularly, the core idea behind our PBC is to learn a robust and accurate mapping from the point annotations to the bounding boxes against the variance of annotated points. To achieve that, a regularization term, namely multi-point consistency, is proposed, which drives the model to generate the consistent bounding box from different point annotations inside the same abnormality. Furthermore, a self-supervision, termed symmetric consistency, is also proposed to deeply exploit the useful information from the weakly annotated data for abnormality localization. Experimental results on RSNA and VinDr-CXR datasets justify the effectiveness of the proposed method. When less than 20% box-level labels are used for training, an improvement of ~5 in mAP can be achieved by our PBC, compared to the current state-of-the-art method (i.e., Point DETR). Code is available at https://github.com/HaozheLiu-ST/Point-Beyond-Class., Accepted by MICCAI-2022

\noindent Traditional L_p norm-restricted image attack algorithms suffer from poor transferability to black box scenarios and poor robustness to defense algorithms. Recent CNN generator-based attack approaches can synthesize unrestricted and semantically meaningful entities to the image, which is shown to be transferable and robust. However, such methods attack images by either synthesizing local adversarial entities, which are only suitable for attacking specific contents or performing global attacks, which are only applicable to a specific image scale. In this paper, we propose a novel Patch Quilting Generative Adversarial Networks (PQ-GAN) to learn the first scale-free CNN generator that can be applied to attack images with arbitrary scales for various computer vision tasks. The principal investigation on transferability of the generated adversarial examples, robustness to defense frameworks, and visual quality assessment show that the proposed PQG-based attack framework outperforms the other nine state-of-the-art adversarial attack approaches when attacking the neural networks trained on two standard evaluation datasets (i.e., ImageNet and CityScapes).

Due to the difficulty of cancer samples collection and annotation, cervical cancer datasets usually exhibit a long-tailed data distribution. When training a detector to detect the cancer cells in a WSI (Whole Slice Image) image captured from the TCT (Thinprep Cytology Test) specimen, head categories (e.g. normal cells and inflammatory cells) typically have a much larger number of samples than tail categories (e.g. cancer cells). Most existing state-of-the-art long-tailed learning methods in object detection focus on category distribution statistics to solve the problem in the long-tailed scenario without considering the "hardness" of each sample. To address this problem, in this work we propose a Grad-Libra Loss that leverages the gradients to dynamically calibrate the degree of hardness of each sample for different categories, and re-balance the gradients of positive and negative samples. Our loss can thus help the detector to put more emphasis on those hard samples in both head and tail categories. Extensive experiments on a long-tailed TCT WSI image dataset show that the mainstream detectors, e.g. RepPoints, FCOS, ATSS, YOLOF, etc. trained using our proposed Gradient-Libra Loss, achieved much higher (7.8%) mAP than that trained using cross-entropy classification loss.

Can we construct an explainable face recognition network able to learn a facial part-based feature like eyes, nose, mouth and so forth, without any manual annotation or additionalsion datasets? In this paper, we propose a generic Explainable Channel Loss (ECLoss) to construct an explainable face recognition network. The explainable network trained with ECLoss can easily learn the facial part-based representation on the target convolutional layer, where an individual channel can detect a certain face part. Our experiments on dozens of datasets show that ECLoss achieves superior explainability metrics, and at the same time improves the performance of face verification without face alignment. In addition, our visualization results also illustrate the effectiveness of the proposed ECLoss., 13 pages, 7 figures, 5 tables

Pyramidal networks are standard methods for multi-scale object detection. Current researches on feature pyramid networks usually adopt layer connections to collect features from certain levels of the feature hierarchy, and do not consider the significant differences among them. We propose a better architecture of feature pyramid networks, named selective multi-scale learning (SMSL), to address this issue. SMSL is efficient and general, which can be integrated in both single-stage and two-stage detectors to boost detection performance, with nearly no extra inference cost. RetinaNet combined with SMSL obtains 1.8\% improvement in AP (from 39.1\% to 40.9\%) on COCO dataset. When integrated with SMSL, two-stage detectors can get around 1.0\% improvement in AP., Accepted by ICANN2021

A long-term video, such as a movie or TV show, is composed of various scenes, each of which represents a series of shots sharing the same semantic story. Spotting the correct scene boundary from the long-term video is a challenging task, since a model must understand the storyline of the video to figure out where a scene starts and ends. To this end, we propose an effective Self-Supervised Learning (SSL) framework to learn better shot representations from unlabeled long-term videos. More specifically, we present an SSL scheme to achieve scene consistency, while exploring considerable data augmentation and shuffling methods to boost the model generalizability. Instead of explicitly learning the scene boundary features as in the previous methods, we introduce a vanilla temporal model with less inductive bias to verify the quality of the shot features. Our method achieves the state-of-the-art performance on the task of Video Scene Segmentation. Additionally, we suggest a more fair and reasonable benchmark to evaluate the performance of Video Scene Segmentation methods. The code is made available., Comment: Accepted to CVPR 2022

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they rely on a classification layer with a closed set of categories. Furthermore, the perturbations generated by these methods may appear in regions easily perceptible to the human visual system (HVS). To circumvent the former problem, we propose a novel algorithm that attacks semantic similarity on feature representations. In this way, we are able to fool classifiers without limiting attacks to a specific dataset. For imperceptibility, we introduce the low-frequency constraint to limit perturbations within high-frequency components, ensuring perceptual similarity between adversarial examples and originals. Extensive experiments on three datasets (CIFAR-10, CIFAR-100, and ImageNet-1K) and three public online platforms indicate that our attack can yield misleading and transferable adversarial examples across architectures and datasets. Additionally, visualization results and quantitative performance (in terms of four different metrics) show that the proposed algorithm generates more imperceptible perturbations than the state-of-the-art methods. Code is made available at., Comment: CVPR 2022 conference (accepted), 18 pages, 17 figure

The activations of Facial Action Units (AUs) mutually influence one another. While the relationship between a pair of AUs can be complex and unique, existing approaches fail to specifically and explicitly represent such cues for each pair of AUs in each facial display. This paper proposes an AU relationship modelling approach that deep learns a unique graph to explicitly describe the relationship between each pair of AUs of the target facial display. Our approach first encodes each AU's activation status and its association with other AUs into a node feature. Then, it learns a pair of multi-dimensional edge features to describe multiple task-specific relationship cues between each pair of AUs. During both node and edge feature learning, our approach also considers the influence of the unique facial display on AUs' relationship by taking the full face representation as an input. Experimental results on BP4D and DISFA datasets show that both node and edge feature learning modules provide large performance improvements for CNN and transformer-based backbones, with our best systems achieving the state-of-the-art AU recognition results. Our approach not only has a strong capability in modelling relationship cues for AU recognition but also can be easily incorporated into various backbones. Our PyTorch code is made available., IJCAI 2022 conference (accepted)

While class activation map (CAM) generated by image classification network has been widely used for weakly supervised object localization (WSOL) and semantic segmentation (WSSS), such classifiers usually focus on discriminative object regions. In this paper, we propose Contrastive learning for Class-agnostic Activation Map (C$^2$AM) generation only using unlabeled image data, without the involvement of image-level supervision. The core idea comes from the observation that i) semantic information of foreground objects usually differs from their backgrounds; ii) foreground objects with similar appearance or background with similar color/texture have similar representations in the feature space. We form the positive and negative pairs based on the above relations and force the network to disentangle foreground and background with a class-agnostic activation map using a novel contrastive loss. As the network is guided to discriminate cross-image foreground-background, the class-agnostic activation maps learned by our approach generate more complete object regions. We successfully extracted from C$^2$AM class-agnostic object bounding boxes for object localization and background cues to refine CAM generated by classification network for semantic segmentation. Extensive experiments on CUB-200-2011, ImageNet-1K, and PASCAL VOC2012 datasets show that both WSOL and WSSS can benefit from the proposed C$^2$AM., Comment: Accepted by CVPR 2022

It has been widely known that CAM (Class Activation Map) usually only activates discriminative object regions and falsely includes lots of object-related backgrounds. As only a fixed set of image-level object labels are available to the WSSS (weakly supervised semantic segmentation) model, it could be very difficult to suppress those diverse background regions consisting of open set objects. In this paper, we propose a novel Cross Language Image Matching (CLIMS) framework, based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress closely-related open background regions. In particular, we design object, background region and text label matching losses to guide the model to excite more reasonable object regions for CAM of each category. In addition, we design a co-occurring background suppression loss to prevent the model from activating closely-related background regions, with a predefined set of class-related background text descriptions. These designs enable the proposed CLIMS to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC2012 dataset show that our CLIMS significantly outperforms the previous state-of-the-art methods., Comment: Accepted by CVPR 2022

Recently, the success of pre-training in text domain has been fully extended to vision, audio, and cross-modal scenarios. The proposed pre-training models of different modalities are showing a rising trend of homogeneity in their model structures, which brings the opportunity to implement different pre-training models within a uniform framework. In this paper, we present TencentPretrain, a toolkit supporting pre-training models of different modalities. The core feature of TencentPretrain is the modular design. The toolkit uniformly divides pre-training models into 5 components: embedding, encoder, target embedding, decoder, and target. As almost all of common modules are provided in each component, users can choose the desired modules from different components to build a complete pre-training model. The modular design enables users to efficiently reproduce existing pre-training models or build brand-new one. We test the toolkit on text, vision, and audio benchmarks and show that it can match the performance of the original implementations.

Employing the latent space of pretrained generators has recently been shown to be an effective means for GAN-based face manipulation. The success of this approach heavily relies on the innate disentanglement of the latent space axes of the generator. However, face manipulation often intends to affect local regions only, while common generators do not tend to have the necessary spatial disentanglement. In this paper, we build on the StyleGAN generator, and present a method that explicitly encourages face manipulation to focus on the intended regions by incorporating learned attention maps. During the generation of the edited image, the attention map serves as a mask that guides a blending between the original features and the modified ones. The guidance for the latent space edits is achieved by employing CLIP, which has recently been shown to be effective for text-driven edits. We perform extensive experiments and show that our method can perform disentangled and controllable face manipulations based on text descriptions by attending to the relevant regions only. Both qualitative and quantitative experimental results demonstrate the superiority of our method for facial region editing over alternative methods.

Implant prosthesis is the most appropriate treatment for dentition defect or dentition loss, which usually involves a surgical guide design process to decide the implant position. However, such design heavily relies on the subjective experiences of dentists. In this paper, a transformer-based Implant Position Regression Network, ImplantFormer, is proposed to automatically predict the implant position based on the oral CBCT data. We creatively propose to predict the implant position using the 2D axial view of the tooth crown area and fit a centerline of the implant to obtain the actual implant position at the tooth root. Convolutional stem and decoder are designed to coarsely extract image features before the operation of patch embedding and integrate multi-level feature maps for robust prediction, respectively. As both long-range relationship and local features are involved, our approach can better represent global information and achieves better location performance. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed ImplantFormer achieves superior performance than existing methods.

Deep convolutional neural network (CNN) based models are vulnerable to the adversarial attacks. One of the possible reasons is that the embedding space of CNN based model is sparse, resulting in a large space for the generation of adversarial samples. In this study, we propose a method, denoted as Dynamic Feature Aggregation, to compress the embedding space with a novel regularization. Particularly, the convex combination between two samples are regarded as the pivot for aggregation. In the embedding space, the selected samples are guided to be similar to the representation of the pivot. On the other side, to mitigate the trivial solution of such regularization, the last fully-connected layer of the model is replaced by an orthogonal classifier, in which the embedding codes for different classes are processed orthogonally and separately. With the regularization and orthogonal classifier, a more compact embedding space can be obtained, which accordingly improves the model robustness against adversarial attacks. An averaging accuracy of 56.91% is achieved by our method on CIFAR-10 against various attack methods, which significantly surpasses a solid baseline (Mixup) by a margin of 37.31%. More surprisingly, empirical results show that, the proposed method can also achieve the state-of-the-art performance for out-of-distribution (OOD) detection, due to the learned compact feature space. An F1 score of 0.937 is achieved by the proposed method, when adopting CIFAR-10 as in-distribution (ID) dataset and LSUN as OOD dataset. Code is available at https://github.com/HaozheLiu-ST/DynamicFeatureAggregation.

Graph is powerful for representing various types of real-world data. The topology (edges' presence) and edges' features of a graph decides the message passing mechanism among vertices within the graph. While most existing approaches only manually define a single-value edge to describe the connectivity or strength of association between a pair of vertices, task-specific and crucial relationship cues may be disregarded by such manually defined topology and single-value edge features. In this paper, we propose the first general graph representation learning framework (called GRATIS) which can generate a strong graph representation with a task-specific topology and task-specific multi-dimensional edge features from any arbitrary input. To learn each edge's presence and multi-dimensional feature, our framework takes both of the corresponding vertices pair and their global contextual information into consideration, enabling the generated graph representation to have a globally optimal message passing mechanism for different down-stream tasks. The principled investigation results achieved for various graph analysis tasks on 11 graph and non-graph datasets show that our GRATIS can not only largely enhance pre-defined graphs but also learns a strong graph representation for non-graph data, with clear performance improvements on all tasks. In particular, the learned topology and multi-dimensional edge features provide complementary task-related cues for graph analysis tasks. Our framework is effective, robust and flexible, and is a plug-and-play module that can be combined with different backbones and Graph Neural Networks (GNNs) to generate a task-specific graph representation from various graph and non-graph data. Our code is made publicly available at https://github.com/SSYSteve/Learning-Graph-Representation-with-Task-specific-Topology-and-Multi-dimensional-Edge-Features.

Object detection has made substantial progress in the last decade, due to the capability of convolution in extracting local context of objects. However, the scales of objects are diverse and current convolution can only process single-scale input. The capability of traditional convolution with a fixed receptive field in dealing with such a scale variance problem, is thus limited. Multi-scale feature representation has been proven to be an effective way to mitigate the scale variance problem. Recent researches mainly adopt partial connection with certain scales, or aggregate features from all scales and focus on the global information across the scales. However, the information across spatial and depth dimensions is ignored. Inspired by this, we propose the multi-scale convolution (MSConv) to handle this problem. Taking into consideration scale, spatial and depth information at the same time, MSConv is able to process multi-scale input more comprehensively. MSConv is effective and computationally efficient, with only a small increase of computational cost. For most of the single-stage object detectors, replacing the traditional convolutions with MSConvs in the detection head can bring more than 2.5\% improvement in AP (on COCO 2017 dataset), with only 3\% increase of FLOPs. MSConv is also flexible and effective for two-stage object detectors. When extended to the mainstream two-stage object detectors, MSConv can bring up to 3.0\% improvement in AP. Our best model under single-scale testing achieves 48.9\% AP on COCO 2017 \textit{test-dev} split, which surpasses many state-of-the-art methods., Accepted by ICTAI2021

This approach builds on two following findings in cognitive science: (i) human cognition partially determines expressed behaviour and is directly linked to true personality traits; and (ii) in dyadic interactions individuals' nonverbal behaviours are influenced by their conversational partner behaviours. In this context, we hypothesise that during a dyadic interaction, a target subject's facial reactions are driven by two main factors, i.e. their internal (person-specific) cognitive process, and the externalised nonverbal behaviours of their conversational partner. Consequently, we propose to represent the target subjects (defined as the listener) person-specific cognition in the form of a person-specific CNN architecture that has unique architectural parameters and depth, which takes audio-visual non-verbal cues displayed by the conversational partner (defined as the speaker) as input, and is able to reproduce the target subject's facial reactions. Each person-specific CNN is explored by the Neural Architecture Search (NAS) and a novel adaptive loss function, which is then represented as a graph representation for recognising the target subject's true personality. Experimental results not only show that the produced graph representations are well associated with target subjects' personality traits in both human-human and human-machine interaction scenarios, and outperform the existing approaches with significant advantages, but also demonstrate that the proposed novel strategies such as adaptive loss, and the end-to-end vertices/edges feature learning, help the proposed approach in learning more reliable personality representations., Submitted to IJCV

Motivation: 3D neuron segmentation is a key step for the neuron digital reconstruction, which is essential for exploring brain circuits and understanding brain functions. However, the fine line-shaped nerve fibers of neuron could spread in a large region, which brings great computational cost to the neuron segmentation. Meanwhile, the strong noises and disconnected nerve fibers bring great challenges to the task. Results: In this paper, we propose a 3D wavelet and deep learning based 3D neuron segmentation method. The neuronal image is first partitioned into neuronal cubes to simplify the segmentation task. Then, we design 3D WaveUNet, the first 3D wavelet integrated encoder-decoder network, to segment the nerve fibers in the cubes; the wavelets could assist the deep networks in suppressing data noises and connecting the broken fibers. We also produce a Neuronal Cube Dataset (NeuCuDa) using the biggest available annotated neuronal image dataset, BigNeuron, to train 3D WaveUNet. Finally, the nerve fibers segmented in cubes are assembled to generate the complete neuron, which is digitally reconstructed using an available automatic tracing algorithm. The experimental results show that our neuron segmentation method could completely extract the target neuron in noisy neuronal images. The integrated 3D wavelets can efficiently improve the performance of 3D neuron segmentation and reconstruction. Availability: The data and codes for this work are available at https://github.com/LiQiufu/3D-WaveUNet., Comment: Bioinformatics accepted paper

Generative Adversarial Networks (GANs) have been widely adopted in various fields. However, existing GANs generally are not able to preserve the manifold of data space, mainly due to the simple representation of discriminator for the real/generated data. To address such open challenges, this paper proposes Manifold-preserved GANs (MaF-GANs), which generalize Wasserstein GANs into high-dimensional form. Specifically, to improve the representation of data, the discriminator in MaF-GANs is designed to map data into a high-dimensional manifold. Furthermore, to stabilize the training of MaF-GANs, an operation with precise and universal solution for any K-Lipschitz continuity, called Topological Consistency is proposed. The effectiveness of the proposed method is justified by both theoretical analysis and empirical results. When adopting DCGAN as the backbone on CelebA (256*256), the proposed method achieved 12.43 FID, which outperforms the state-of-the-art model like Realness GAN (23.51 FID) by a large margin. Code will be made publicly available.

The Coronavirus disease 2019 (COVID-19) has rapidly spread all over the world since its first report in December 2019 and thoracic computed tomography (CT) has become one of the main tools for its diagnosis. In recent years, deep learning-based approaches have shown impressive performance in myriad image recognition tasks. However, they usually require a large number of annotated data for training. Inspired by Ground Glass Opacity (GGO), a common finding in COIVD-19 patient's CT scans, we proposed in this paper a novel self-supervised pretraining method based on pseudo lesions generation and restoration for COVID-19 diagnosis. We used Perlin noise, a gradient noise based mathematical model, to generate lesion-like patterns, which were then randomly pasted to the lung regions of normal CT images to generate pseudo COVID-19 images. The pairs of normal and pseudo COVID-19 images were then used to train an encoder-decoder architecture based U-Net for image restoration, which does not require any labelled data. The pretrained encoder was then fine-tuned using labelled data for COVID-19 diagnosis task. Two public COVID-19 diagnosis datasets made up of CT images were employed for evaluation. Comprehensive experimental results demonstrated that the proposed self-supervised learning approach could extract better feature representation for COVID-19 diagnosis and the accuracy of the proposed method outperformed the supervised model pretrained on large scale images by 6.57% and 3.03% on SARS-CoV-2 dataset and Jinan COVID-19 dataset, respectively.

Considering the scarcity of medical data, most datasets in medical image analysis are an order of magnitude smaller than those of natural images. However, most Network Architecture Search (NAS) approaches in medical images focused on specific datasets and did not take into account the generalization ability of the learned architectures on unseen datasets as well as different domains. In this paper, we address this point by proposing to search for generalizable U-shape architectures on a composited dataset that mixes medical images from multiple segmentation tasks and domains creatively, which is named MixSearch. Specifically, we propose a novel approach to mix multiple small-scale datasets from multiple domains and segmentation tasks to produce a large-scale dataset. Then, a novel weaved encoder-decoder structure is designed to search for a generalized segmentation network in both cell-level and network-level. The network produced by the proposed MixSearch framework achieves state-of-the-art results compared with advanced encoder-decoder networks across various datasets.

Although significant progress has been made in synthesizing high-quality and visually realistic face images by unconditional Generative Adversarial Networks (GANs), there still lacks of control over the generation process in order to achieve semantic face editing. In addition, it remains very challenging to maintain other face information untouched while editing the target attributes. In this paper, we propose a novel learning framework, called GuidedStyle, to achieve semantic face editing on StyleGAN by guiding the image generation process with a knowledge network. Furthermore, we allow an attention mechanism in StyleGAN generator to adaptively select a single layer for style manipulation. As a result, our method is able to perform disentangled and controllable edits along various attributes, including smiling, eyeglasses, gender, mustache and hair color. Both qualitative and quantitative results demonstrate the superiority of our method over other competing methods for semantic face editing. Moreover, we show that our model can be also applied to different types of real and artistic face editing, demonstrating strong generalization ability.

Deep convolutional neural network (CNN) achieves remarkable performance for medical image analysis. UNet is the primary source in the performance of 3D CNN architectures for medical imaging tasks, including brain tumor segmentation. The skip connection in the UNet architecture concatenates features from both encoder and decoder paths to extract multi-contextual information from image data. The multi-scaled features play an essential role in brain tumor segmentation. However, the limited use of features can degrade the performance of the UNet approach for segmentation. In this paper, we propose a modified UNet architecture for brain tumor segmentation. In the proposed architecture, we used densely connected blocks in both encoder and decoder paths to extract multi-contextual information from the concept of feature reusability. In addition, residual-inception blocks (RIB) are used to extract the local and global information by merging features of different kernel sizes. We validate the proposed architecture on the multi-modal brain tumor segmentation challenge (BRATS) 2020 testing dataset. The dice (DSC) scores of the whole tumor (WT), tumor core (TC), and enhancing tumor (ET) are 89.12%, 84.74%, and 79.12%, respectively., Accepted for MICCAI 2020 Brain Lesions (BrainLes) Workshop

We propose a geometry constrained network, termed GC-Net, for weakly supervised object localization (WSOL). GC-Net consists of three modules: a detector, a generator and a classifier. The detector predicts the object location defined by a set of coefficients describing a geometric shape (i.e. ellipse or rectangle), which is geometrically constrained by the mask produced by the generator. The classifier takes the resulting masked images as input and performs two complementary classification tasks for the object and background. To make the mask more compact and more complete, we propose a novel multi-task loss function that takes into account area of the geometric shape, the categorical cross-entropy and the negative entropy. In contrast to previous approaches, GC-Net is trained end-to-end and predict object location without any post-processing (e.g. thresholding) that may require additional tuning. Extensive experiments on the CUB-200-2011 and ILSVRC2012 datasets show that GC-Net outperforms state-of-the-art methods by a large margin. Our source code is available at https://github.com/lwzeng/GC-Net., This paper (ID 5424) is accepted to ECCV 2020

In deep networks, the lost data details significantly degrade the performances of image segmentation. In this paper, we propose to apply Discrete Wavelet Transform (DWT) to extract the data details during feature map down-sampling, and adopt Inverse DWT (IDWT) with the extracted details during the up-sampling to recover the details. We firstly transform DWT/IDWT as general network layers, which are applicable to 1D/2D/3D data and various wavelets like Haar, Cohen, and Daubechies, etc. Then, we design wavelet integrated deep networks for image segmentation (WaveSNets) based on various architectures, including U-Net, SegNet, and DeepLabv3+. Due to the effectiveness of the DWT/IDWT in processing data details, experimental results on CamVid, Pascal VOC, and Cityscapes show that our WaveSNets achieve better segmentation performances than their vanilla versions., 7 pages, 7 figures

Though GAN (Generative Adversarial Networks) based technique has greatly advanced the performance of image synthesis and face translation, only few works available in literature provide region based style encoding and translation. We propose in this paper a region-wise normalization framework, for region level face translation. While per-region style is encoded using available approach, we build a so called RIN (region-wise normalization) block to individually inject the styles into per-region feature maps and then fuse them for following convolution and upsampling. Both shape and texture of different regions can thus be translated to various target styles. A region matching loss has also been proposed to significantly reduce the inference between regions during the translation process. Extensive experiments on three publicly available datasets, i.e. Morph, RaFD and CelebAMask-HQ, suggest that our approach demonstrate a large improvement over state-of-the-art methods like StarGAN, SEAN and FUNIT. Our approach has further advantages in precise control of the regions to be translated. As a result, region level expression changes and step by step make up can be achieved. The video demo is available at https://youtu.be/ceRqsbzXAfk., Comment: 13 pages, 13 figures

The brain tumor segmentation task aims to classify tissue into the whole tumor (WT), tumor core (TC), and enhancing tumor (ET) classes using multimodel MRI images. Quantitative analysis of brain tumors is critical for clinical decision making. While manual segmentation is tedious, time-consuming, and subjective, this task is at the same time very challenging to automatic segmentation methods. Thanks to the powerful learning ability, convolutional neural networks (CNNs), mainly fully convolutional networks, have shown promising brain tumor segmentation. This paper further boosts the performance of brain tumor segmentation by proposing hyperdense inception 3D UNet (HI-Net), which captures multi-scale information by stacking factorization of 3D weighted convolutional layers in the residual inception block. We use hyper dense connections among factorized convolutional layers to extract more contexual information, with the help of features reusability. We use a dice loss function to cope with class imbalances. We validate the proposed architecture on the multi-modal brain tumor segmentation challenges (BRATS) 2020 testing dataset. Preliminary results on the BRATS 2020 testing set show that achieved by our proposed approach, the dice (DSC) scores of ET, WT, and TC are 0.79457, 0.87494, and 0.83712, respectively., Comment: Accepted for MICCAI BraTS 2020

Due to the wide existence and large morphological variances of nuclei, accurate nuclei instance segmentation is still one of the most challenging tasks in computational pathology. The annotating of nuclei instances, requiring experienced pathologists to manually draw the contours, is extremely laborious and expensive, which often results in the deficiency of annotated data. The deep learning based segmentation approaches, which highly rely on the quantity of training data, are difficult to fully demonstrate their capacity in this area. In this paper, we propose a novel self-supervised learning framework to deeply exploit the capacity of widely-used convolutional neural networks (CNNs) on the nuclei instance segmentation task. The proposed approach involves two sub-tasks (i.e., scale-wise triplet learning and count ranking), which enable neural networks to implicitly leverage the prior-knowledge of nuclei size and quantity, and accordingly mine the instance-aware feature representations from the raw data. Experimental results on the publicly available MoNuSeg dataset show that the proposed self-supervised learning approach can remarkably boost the segmentation accuracy of nuclei instance---a new state-of-the-art average Aggregated Jaccard Index (AJI) of 70.63%, is achieved by our self-supervised ResUNet-101. To our best knowledge, this is the first work focusing on the self-supervised learning for instance segmentation., Comment: MICCAI 2020; The first two authors contributed equally

Domain shift between medical images from multicentres is still an open question for the community, which degrades the generalization performance of deep learning models. Generative adversarial network (GAN), which synthesize plausible images, is one of the potential solutions to address the problem. However, the existing GAN-based approaches are prone to fail at preserving image-objects in image-to-image (I2I) translation, which reduces their practicality on domain adaptation tasks. In this paper, we propose a novel GAN (namely MI$^2$GAN) to maintain image-contents during cross-domain I2I translation. Particularly, we disentangle the content features from domain information for both the source and translated images, and then maximize the mutual information between the disentangled content features to preserve the image-objects. The proposed MI$^2$GAN is evaluated on two tasks---polyp segmentation using colonoscopic images and the segmentation of optic disc and cup in fundus images. The experimental results demonstrate that the proposed MI$^2$GAN can not only generate elegant translated images, but also significantly improve the generalization performance of widely used deep learning networks (e.g., U-Net)., Comment: The first two authors contributed equally

Facial actions are spatio-temporal signals by nature, and therefore their modeling is crucially dependent on the availability of temporal information. In this paper, we focus on inferring such temporal dynamics of facial actions when no explicit temporal information is available, i.e. from still images. We present a novel approach to capture multiple scales of such temporal dynamics, with an application to facial Action Unit (AU) intensity estimation and dimensional affect estimation. In particular, 1) we propose a framework that infers a dynamic representation (DR) from a still image, which captures the bi-directional flow of time within a short time-window centered at the input image; 2) we show that we can train our method without the need of explicitly generating target representations, allowing the network to represent dynamics more broadly; and 3) we propose to apply a multiple temporal scale approach that infers DRs for different window lengths (MDR) from a still image. We empirically validate the value of our approach on the task of frame ranking, and show how our proposed MDR attains state of the art results on BP4D for AU intensity estimation and on SEMAINE for dimensional affect estimation, using only still images at test time., 10 pages, 5 figures

Despite the significant success in image-to-image translation and latent representation based facial attribute editing and expression synthesis, the existing approaches still have limitations in the sharpness of details, distinct image translation and identity preservation. To address these issues, we propose a Texture Deformation Based GAN, namely TDB-GAN, to disentangle texture from original image and transfers domains based on the extracted texture. The approach utilizes the texture to transfer facial attributes and expressions without the consideration of the object pose. This leads to shaper details and more distinct visual effect of the synthesized faces. In addition, it brings the faster convergence during training. The effectiveness of the proposed method is validated through extensive ablation studies. We also evaluate our approach qualitatively and quantitatively on facial attribute and facial expression synthesis. The results on both the CelebA and RaFD datasets suggest that Texture Deformation Based GAN achieves better performance., 10 pages, 6 figures, 3 tables

Witnessed the development of deep learning in recent years, increasing number of researches try to adopt deep learning model for medical image analysis. However, the usage of deep learning networks for the pathological image analysis encounters several challenges, e.g. high resolution (gigapixel) of pathological images and lack of annotations of cancer areas. To address the challenges, we proposed a complete framework for the pathological image classification, which consists of a novel training strategy, namely reversed active learning (RAL), and an advanced network, namely atrous DenseNet (ADN). The proposed RAL can remove the mislabel patches in the training set. The refined training set can then be used to train widely used deep learning networks, e.g. VGG-16, ResNets, etc. A novel deep learning network, i.e. atrous DenseNet (ADN), is also proposed for the classification of pathological images. The proposed ADN achieves multi-scale feature extraction by integrating the atrous convolutions to the Dense Block. The proposed RAL and ADN have been evaluated on two pathological datasets, i.e. BACH and CCG. The experimental results demonstrate the excellent performance of the proposed ADN + RAL framework, i.e. the average patch-level ACAs of 94.10% and 92.05% on BACH and CCG validation sets were achieved.

Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multi-parametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumor is a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in pre-operative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST/RANO criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that underwent gross total resection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset., Comment: The International Multimodal Brain Tumor Segmentation (BraTS) Challenge

Breast cancer is the second most common malignancy among women and has become a major public health problem in current society. Traditional breast cancer identification requires experienced pathologists to carefully read the breast slice, which is laborious and suffers from inter-observer variations. Consequently, an automatic classification framework for breast cancer identification is worthwhile to develop. Recent years witnessed the development of deep learning technique. Increasing number of medical applications start to use deep learning to improve diagnosis accuracy. In this paper, we proposed a novel training strategy, namely reversed active learning (RAL), to train network to automatically classify breast cancer images. Our RAL is applied to the training set of a simple convolutional neural network (CNN) to remove mislabeled images. We evaluate the CNN trained with RAL on publicly available ICIAR 2018 Breast Cancer Dataset (IBCD). The experimental results show that our RAL increases the slice-based accuracy of CNN from 93.75% to 96.25%.

We proposed a two stage framework with only one network to analyze skin lesion images, we firstly trained a convolutional network to classify these images, and cropped the import regions which the network has the maximum activation value. In the second stage, we retrained this CNN with the image regions extracted from stage one and output the final probabilities. The two stage framework achieved a mean AUC of 0.857 in ISIC-2017 skin lesion validation set and is 0.04 higher than that of the original inputs, 0.821.

There is a neglected fact in the traditional machine learning methods that the data sampling can actually lead to the solution sampling. We consider this observation to be important because having the solution sampling available makes the variable distribution estimation, which is a problem in many learning-related applications, more tractable. In this paper, we implement this idea on correlation filter, which has attracted much attention in the past few years due to its high performance with a low computational cost. More specifically, we propose a new method, named latent constrained correlation filters (LCCF) by mapping the correlation filters to a given latent subspace, in which we establish a new learning framework that embeds distribution-related constraints into the original problem. We further introduce a subspace based alternating direction method of multipliers (SADMM) to efficiently solve the optimization problem, which is proved to converge at the saddle point. Our approach is successfully applied to two different tasks inclduing eye localization and car detection. Extensive experiments demonstrate that LCCF outperforms the state-of-the-art methods when samples are suffered from noise and occlusion., Comment: There are small problems and theories need to be perfected

We present a method for discovering and exploiting object specific deep learning features and use face detection as a case study. Motivated by the observation that certain convolutional channels of a Convolutional Neural Network (CNN) exhibit object specific responses, we seek to discover and exploit the convolutional channels of a CNN in which neurons are activated by the presence of specific objects in the input image. A method for explicitly fine-tuning a pre-trained CNN to induce an object specific channel (OSC) and systematically identifying it for the human face object has been developed. Based on the basic OSC features, we introduce a multi-resolution approach to constructing robust face heatmaps for fast face detection in unconstrained settings. We show that multi-resolution OSC can be used to develop state of the art face detectors which have the advantage of being simple and compact.

In this paper, we propose a novel local feature, called Local Orientation Adaptive Descriptor (LOAD), to capture regional texture in an image. In LOAD, we proposed to define point description on an Adaptive Coordinate System (ACS), adopt a binary sequence descriptor to capture relationships between one point and its neighbors and use multi-scale strategy to enhance the discriminative power of the descriptor. The proposed LOAD enjoys not only discriminative power to capture the texture information, but also has strong robustness to illumination variation and image rotation. Extensive experiments on benchmark data sets of texture classification and real-world material recognition show that the proposed LOAD yields the state-of-the-art performance. It is worth to mention that we achieve a 65.4\% classification accuracy-- which is, to the best of our knowledge, the highest record by far --on Flickr Material Database by using a single feature. Moreover, by combining LOAD with the feature extracted by Convolutional Neural Networks (CNN), we obtain significantly better performance than both the LOAD and CNN. This result confirms that the LOAD is complementary to the learning-based features., 13 pages, 7 figures