Search

In steady-state visual-evoked potential (SSVEP) based brain-computer interfaces (BCIs), existing detection algorithms utilizing spatial filters like task-related component analysis (TRCA) derive the spatial filters mainly through maximizing the inter-trial similarity between the combined signals over the training set. Although they achieve by far the best classification performance in SSVEP-based BCIs, some important problems are still unresolved. Especially, the mechanism of how spatial filters cancel the background noise in brain signals and optimize the signal-to-noise ratio (SNR) of SSVEPs is still not figured out. Therefore, to solve these problems, in this paper a new perspective of spatial filter design is proposed. Specifically, a linear generative signal model of SSVEP is adopted and the spatial filters are obtained automatically through maximum likelihood estimation of source signals and channel vectors. In the same time, the relation between maximum likelihood estimation and signal-to-noise ratio (SNR) maximization is discussed. Through a step-by-step formulation, this paper provides a theoretical justification for those conventional algorithms utilizing spatial filters. As for the classification performance, the proposed scheme is tested on a benchmark dataset of 35 subjects. Experiment results show that the classification performance of the proposed scheme is competitive against three benchmark algorithms, which include TRCA. Especially, the proposed scheme achieves a fair performance improvement over the benchmark methods in the cases where a shorter time window, or a larger number of electrodes, or a smaller number of training blocks are adopted. [ABSTRACT FROM AUTHOR]

This paper studies the problem of learning the conditional distribution of a high-dimensional output given an input, where the output and input may belong to two different domains, e.g., the output is a photo image and the input is a sketch image. We solve this problem by cooperative training of a fast thinking initializer and slow thinking solver. The initializer generates the output directly by a non-linear transformation of the input as well as a noise vector that accounts for latent variability in the output. The slow thinking solver learns an objective function in the form of a conditional energy function, so that the output can be generated by optimizing the objective function, or more rigorously by sampling from the conditional energy-based model. We propose to learn the two models jointly, where the fast thinking initializer serves to initialize the sampling of the slow thinking solver, and the solver refines the initial output by an iterative algorithm. The solver learns from the difference between the refined output and the observed output, while the initializer learns from how the solver refines its initial output. We demonstrate the effectiveness of the proposed method on various conditional learning tasks, e.g., class-to-image generation, image-to-image translation, and image recovery. The advantage of our method over GAN-based methods is that our method is equipped with a slow thinking process that refines the solution guided by a learned objective function. [ABSTRACT FROM AUTHOR]

Full projector compensation aims to modify a projector input image to compensate for both geometric and photometric disturbance of the projection surface. Traditional methods usually solve the two parts separately and may suffer from suboptimal solutions. In this paper, we propose the first end-to-end differentiable solution, named CompenNeSt++, to solve the two problems jointly. First, we propose a novel geometric correction subnet, named WarpingNet, which is designed with a cascaded coarse-to-fine structure to learn the sampling grid directly from sampling images. Second, we propose a novel photometric compensation subnet, named CompenNeSt, which is designed with a siamese architecture to capture the photometric interactions between the projection surface and the projected images, and to use such information to compensate the geometrically corrected images. By concatenating WarpingNet with CompenNeSt, CompenNeSt++ accomplishes full projector compensation and is end-to-end trainable. Third, to improve practicability, we propose a novel synthetic data-based pre-training strategy to significantly reduce the number of training images and training time. Moreover, we construct the first setup-independent full compensation benchmark to facilitate future studies. In thorough experiments, our method shows clear advantages over prior art with promising compensation quality and meanwhile being practically convenient. [ABSTRACT FROM AUTHOR]

Instance segmentation needs to locate all instances in an image correctly and segment each instance precisely. Currently, the most dominant methods for instance segmentation take object detection as a pre-task. However, they rely on the accuracy of object detection incredibly. If the pre-task cannot predict an accurate bounding box, the performance of instance segmentation will degenerate. In this paper, we present a novel method for instance segmentation to solve this problem, which is called Segmenting Beyond the Bounding Box (S3B-Net). Our S3B-Net designs a sub-network to help instance segmentation methods based on object detection to segment the part of an instance beyond the bounding box. Specifically, the sub-network first predicts a two-dimensional pixel embedding for each pixel. Then, the Gaussian function is employed to calculate a pixel’s probability belongs to a corresponding instance according to the two-dimensional pixel embedding. Finally, the output of the sub-network combines with the output of instance segmentation based on object detection to generate a more precise instance mask. Our sub-network can easily extend on the existing instance segmentation method based on object detection to segment instance beyond the bounding box. We do our experiments on dominant instance segmentation datasets, such as the COCO dataset and Cityscapes dataset. The results show that our method can achieve 6.8 points gain compared with the baseline Mask R-CNN with ResNet-50-FPN in Cityscapes datasets, and 1.7 points gain with ResNet-101-FPN-DCN in COCO datasets. Our S3B-Net outperforms the previous state-of-the-art instance segmentation method, which proves our method is competitive. The source code of our method will be made available. [ABSTRACT FROM AUTHOR]

Accurate solar photovoltaic (PV) generation forecast is critical to the reliable and economic operation of a modern power system. In practice, due to various faulty issues in the sensor, communication, or database system, the historical and online measurement data may not be always complete, and the missing data could dramatically degrade the forecasting model's accuracy. To solve this problem, this paper proposes an integrated missing-data tolerant model for probabilistic PV power generation forecasting. Taking historical PV generations as input, this model is based on a recursive long short-term memory network (Rec-LSTM), which can provide multi-step ahead forecasting of the probability distribution of PV generation. The unobserved input data will be imputed recursively based on the model output at the previous time step. During the training process, the imputations and forecasting values are iteratively updated by the negative log-likelihood loss function. As a salient advantage, this method can deal with data missing scenarios at both offline and online stages. Numerical experiments are conducted on two one-year datasets from Australia and Singapore, respectively. Probabilistic forecasting for both large-scale and small-scale building-level PV power generation is tested at the time resolution of 15 mins. Testing results show the proposed method can achieve superior probabilistic prediction accuracy as well as strong robustness under various data missing scenarios, compared to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

As an emulous alternative to deep neural networks, Deep Forest emerges with features like low complexity, fewer hyper-parameters, and good robustness, which are predominantly desired in distributed computing applications and ecosystems. Recently, an efficient distributed Deep Forest system, named ForestLayer, was proposed, designing a fine-grained sub-Forest-based task-parallel algorithm to improve the parallel computing efficiency of Deep Forest. However, the sub-Forest splitting of ForestLayer is static and one-off without adaptability to the computing environment, nevertheless, the size of splitting granularity has a significant impact on the system performance. To further improve the computing efficiency and scalability of the distributed Deep Forest, in this paper, we propose a novel distributed Deep Forest algorithm, named BLB-gcForest (Bag of Little Bootstraps-gcForest), which augments the gcForest (multi-Grained Cascade Forest) approach for constructing Deep Forest. BLB-gcForest carries out parallel computation for each tree in sub-Forests at a finer parallel granularity and integrates with the Bag of Little Bootstraps (BLB) mechanism to reduce massive transmitted feature instances for Cascade Forest Layers, utterly improving both computation efficiency and communication efficiency. Moreover, to solve the problem of the forest splitting granularity, we further design an adaptive sub-Forest splitting algorithm to ensure the maximum resource utilization for parallel computation of each sub-Forest. Experimental results on four well-known large-scale datasets, namely YEAST, LETTER, MNIST, CIFAR10, show that the training efficiency of BLB-gcForest achieves up to 20.3x and 1.64x speedups compared with the state-of-the-art gcForest and ForestLayer, respectively while guaranteeing higher accuracy and better robustness [ABSTRACT FROM AUTHOR]

We study network pruning which aims to remove redundant channels/kernels and hence speed up the inference of deep networks. Existing pruning methods either train from scratch with sparsity constraints or minimize the reconstruction error between the feature maps of the pre-trained models and the compressed ones. Both strategies suffer from some limitations: the former kind is computationally expensive and difficult to converge, while the latter kind optimizes the reconstruction error but ignores the discriminative power of channels. In this paper, we propose a simple-yet-effective method called discrimination-aware channel pruning (DCP) to choose the channels that actually contribute to the discriminative power. To this end, we first introduce additional discrimination-aware losses into the network to increase the discriminative power of the intermediate layers. Next, we select the most discriminative channels for each layer by considering the discrimination-aware loss and the reconstruction error, simultaneously. We then formulate channel pruning as a sparsity-inducing optimization problem with a convex objective and propose a greedy algorithm to solve the resultant problem. Note that a channel (3D tensor) often consists of a set of kernels (each with a 2D matrix). Besides the redundancy in channels, some kernels in a channel may also be redundant and fail to contribute to the discriminative power of the network, resulting in kernel level redundancy. To solve this issue, we propose a discrimination-aware kernel pruning (DKP) method to further compress deep networks by removing redundant kernels. To avoid manually determining the pruning rate for each layer, we propose two adaptive stopping conditions to automatically determine the number of selected channels/kernels. The proposed adaptive stopping conditions tend to yield more efficient models with better performance in practice. Extensive experiments on both image classification and face recognition demonstrate the effectiveness of our methods. For example, on ILSVRC-12, the resultant ResNet-50 model with 30 percent reduction of channels even outperforms the baseline model by 0.36 percent in terms of Top-1 accuracy. We also deploy the pruned models on a smartphone (equipped with a Qualcomm Snapdragon 845 processor). The pruned MobileNetV1 and MobileNetV2 achieve 1.93× and 1.42× inference acceleration on the mobile device, respectively, with negligible performance degradation. The source code and the pre-trained models are available at https://github.com/SCUT-AILab/DCP. [ABSTRACT FROM AUTHOR]

This paper proposes a gaze correction and animation method for high-resolution, unconstrained portrait images, which can be trained without the gaze angle and the head pose annotations. Common gaze-correction methods usually require annotating training data with precise gaze, and head pose information. Solving this problem using an unsupervised method remains an open problem, especially for high-resolution face images in the wild, which are not easy to annotate with gaze and head pose labels. To address this issue, we first create two new portrait datasets: CelebGaze ($256 \times 256$) and high-resolution CelebHQGaze ($512 \times 512$). Second, we formulate the gaze correction task as an image inpainting problem, addressed using a Gaze Correction Module (GCM) and a Gaze Animation Module (GAM). Moreover, we propose an unsupervised training strategy, i.e., Synthesis-As-Training, to learn the correlation between the eye region features and the gaze angle. As a result, we can use the learned latent space for gaze animation with semantic interpolation in this space. Moreover, to alleviate both the memory and the computational costs in the training and the inference stage, we propose a Coarse-to-Fine Module (CFM) integrated with GCM and GAM. Extensive experiments validate the effectiveness of our method for both the gaze correction and the gaze animation tasks in both low and high-resolution face datasets in the wild and demonstrate the superiority of our method with respect to the state of the art. [ABSTRACT FROM AUTHOR]

Existing video captioning methods usually ignore the important fine-grained semantic attributes, the video diversity, as well as the association and motion state between objects within and between frames. Thus, they cannot adapt to small sample data sets. To solve the above problems, this paper proposes a novel video captioning model and an adversarial reinforcement learning strategy. Firstly, an object-scene relational graph model is designed based on the object detector and scene segmenter to express the association features. The graph is encoded by the graph neural network to enrich the expression of visual features. Meanwhile, a trajectory-based feature representation model is designed to replace the previous data-driven method to extract motion and attribute information, so as to analyze the object motion in the time domain and establish the connection between the visual content and language under small data sets. Finally, an adversarial reinforcement learning strategy and a multi- branch discriminator are designed to learn the relationship between the visual content and corresponding words so that rich language knowledge is integrated into the model. Experimental results on three standard datasets and one small sample dataset indicate that our proposed method achieves state-of-the-art performance. Also, the ablation experiments and visualization results verify the effectiveness of proposed each strategy. [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]

The deep learning based methods have improved the visual tracking precision significantly. However, the background distraction and the high precise localization remain challenging problems. Despite that some methods have fused the deep and shallow layer features to solve these problems, the existing fusion methods, like simply concatenating or adding the features from the different layers, cannot take the advantage of both the deep and shallow layer features fully. In this paper, we propose a new adaptive feature fusion method, called the instance-based feature pyramid (IBFP) to obtain the discriminative high-resolution feature, which not only inherits the discriminative information from the deep layer feature, but also keeps the high precision localization information of the shallow layer feature. For utilizing the deep and shallow features effectively, we design an instance-based upsampling (IBU) module to fuse them, and a compressed space channel selection (CSCS) module to re-weight the feature channels adaptively. We insert the IBU and CSCS modules in the Siamese tracker for end-to-end training and testing. By using the proposed IBU and CSCS modules, we fuse the deep and shallow features in a series manner. Experiments on large-scale benchmark datasets demonstrate that the proposed modules boost the capabilities of distinguishing the targets and the similar distractors and perform favorably against the state-of-the-art. [ABSTRACT FROM AUTHOR]

Federated meta-learning (FML) has emerged as a promising paradigm to cope with the data limitation and heterogeneity challenges in today’s edge learning arena. However, its performance is often limited by slow convergence and corresponding low communication efficiency. In addition, since the available radio spectrum and IoT devices’ energy capacity are usually insufficient, it is crucial to control the resource allocation and energy consumption when deploying FML in practical wireless networks. To overcome the challenges, in this paper, we rigorously analyze the contribution of each device to the global loss reduction in each round and develop an FML algorithm (called NUFM) with a non-uniform device selection scheme to accelerate the convergence. After that, we formulate a resource allocation problem integrating NUFM in multi-access wireless systems to jointly improve the convergence rate and minimize the wall-clock time along with energy cost. By deconstructing the original problem step by step, we devise a joint device selection and resource allocation strategy to solve the problem with theoretical guarantees. Further, we show that the computational complexity of NUFM can be reduced from $O(d^{2})$ to $O(d)$ (with the model dimension $d$) via combining two first-order approximation techniques. Extensive simulation results demonstrate the effectiveness and superiority of the proposed methods in comparison with existing baselines. [ABSTRACT FROM AUTHOR]

Depth estimation from a camera is an important task for 3D perception. Recently, without using the labeled ground truth of depth map, a self-supervised deep learning network can use relative pose to synthesize the target image from the reference image, and the photometric error between synthesized reference image and real one is used as self-supervisory signal. In this paper, we propose a novel self-supervised depth estimation network, which takes advantage of the quadtree constraint to optimize the depth estimation network. Based on the quadtree constraint, the photometric loss and depth loss of quadtree are proposed. In order to solve the problem that multiple depth values in repeated structures and uniform texture regions can cause relatively low photometric loss, we use quadtree-based photometric loss, which calculates the averaged photometric loss in quadtree blocks instead of the pixel-wise loss. For the problem of imbalanced depth distribution, we use quadtree depth loss, which constrains the depth inconsistency within quadtree blocks. The depth estimation network is composed of deep fusion module and cross-layer feature fusion module, which can better extract the feature information of RGB image and sparse keypoints depths, and makes full use of the detail information of the shallow feature map and the semantic information of the deep feature map to enrich the feature information extraction. Experimental results demonstrate that our method outperforms the state-of-the-art approaches of depth estimation. [ABSTRACT FROM AUTHOR]

Zero-shot classification is a promising paradigm to solve an applicable problem when the training classes and test classes are disjoint. Achieving this usually needs experts to externalize their domain knowledge by manually specifying a class-attribute matrix to define which classes have which attributes. Designing a suitable class-attribute matrix is the key to the subsequent procedure, but this design process is tedious and trial-and-error with no guidance. This paper proposes a visual explainable active learning approach with its design and implementation called semantic navigator to solve the above problems. This approach promotes human-AI teaming with four actions (ask, explain, recommend, respond) in each interaction loop. The machine asks contrastive questions to guide humans in the thinking process of attributes. A novel visualization called semantic map explains the current status of the machine. Therefore analysts can better understand why the machine misclassifies objects. Moreover, the machine recommends the labels of classes for each attribute to ease the labeling burden. Finally, humans can steer the model by modifying the labels interactively, and the machine adjusts its recommendations. The visual explainable active learning approach improves humans' efficiency of building zero-shot classification models interactively, compared with the method without guidance. We justify our results with user studies using the standard benchmarks for zero-shot classification. [ABSTRACT FROM AUTHOR]

Due to the discrepancy of different devices for fundus image collection, a well-trained neural network is usually unsuitable for another new dataset. To solve this problem, the unsupervised domain adaptation strategy attracts a lot of attentions. In this paper, we propose an unsupervised domain adaptation method based image synthesis and feature alignment (ISFA) method to segment optic disc and cup on fundus images. The GAN-based image synthesis (IS) mechanism along with the boundary information of optic disc and cup is utilized to generate target-like query images, which serves as the intermediate latent space between source domain and target domain images to alleviate the domain shift problem. Specifically, we use content and style feature alignment (CSFA) to ensure the feature consistency among source domain images, target-like query images and target domain images. The adversarial learning is used to extract domain-invariant features for output-level feature alignment (OLFA). To enhance the representation ability of domain-invariant boundary structure information, we introduce the edge attention module (EAM) for low-level feature maps. Eventually, we train our proposed method on the training set of the REFUGE challenge dataset and test it on Drishti-GS and RIM-ONE_r3 datasets. On the Drishti-GS dataset, our method achieves about 3% improvement of Dice on optic cup segmentation over the next best method. We comprehensively discuss the robustness of our method for small dataset domain adaptation. The experimental results also demonstrate the effectiveness of our method. Our code is available at https://github.com/thinkobj/ISFA. [ABSTRACT FROM AUTHOR]

In this paper, we study asynchronous federated learning (FL) in a wireless distributed learning network (WDLN). To allow each edge device to use its local data more efficiently via asynchronous FL, transmission scheduling in the WDLN for asynchronous FL should be carefully determined considering system uncertainties, such as time-varying channel and stochastic data arrivals, and the scarce radio resources in the WDLN. To address this, we propose a metric, called an effectivity score, which represents the amount of learning from asynchronous FL. We then formulate an Asynchronous Learning-aware transmission Scheduling (ALS) problem to maximize the effectivity score and develop three ALS algorithms, called ALSA-PI, BALSA, and BALSA-PO, to solve it. If the statistical information about the uncertainties is known, the problem can be optimally and efficiently solved by ALSA-PI. Even if not, it can be still optimally solved by BALSA that learns the uncertainties based on a Bayesian approach using the state information reported from devices. BALSA-PO suboptimally solves the problem, but it addresses a more restrictive WDLN in practice, where the AP can observe a limited state information compared with the information used in BALSA. We show via simulations that the models trained by our ALS algorithms achieve performances close to that by an ideal benchmark and outperform those by other state-of-the-art baseline scheduling algorithms in terms of model accuracy, training loss, learning speed, and robustness of learning. These results demonstrate that the adaptive scheduling strategy in our ALS algorithms is effective to asynchronous FL. [ABSTRACT FROM AUTHOR]

In the task of person re-identification, the attention mechanism and fine-grained information have been proved to be effective. However, it has been observed that models often focus on the extraction of features with strong discrimination, and neglect other valuable features. The extracted fine-grained information may include redundancies. In addition, current methods lack an effective scheme to remove background interference. Therefore, this paper proposes the feature refinement and filter network to solve the above problems from three aspects: first, by weakening the high response features, we aim to identify highly valuable features and extract the complete features of persons, thereby enhancing the robustness of the model; second, by positioning and intercepting the high response areas of persons, we eliminate the interference arising from background information and strengthen the response of the model to the complete features of persons; finally, valuable fine-grained features are selected using a multi-branch attention network for person re-identification to enhance the performance of the model. Our extensive experiments on the benchmark Market-1501, DukeMTMC-reID, CUHK03 and MSMT17 person re-identification datasets demonstrate that the performance of our method is comparable to that of state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

When running in Parameter Server (PS), the Distributed Stochastic Gradient Descent (D-SGD) incurs significant communication delays and huge communication overhead due to the model synchronization. Moreover, considering the heterogeneity of computational capability among workers, traditional synchronization modes incur under-utilization of computational resources because fast workers have to wait for slow ones finishing the computation. Although our previous work OSP can effectively solve these problems by overlapping the computation and communication procedures and allowing adaptive multiple local updates in distributed training, it causes the staleness problem brought by the overlap, yielding a performance degradation. In this paper, we propose a new method named LOSP by introducing local compensation to our previous synchronization mechanism, which mitigates adverse effects caused by the overlapping synchronization. We theoretically prove that LOSP (1) preserves the same convergence rate as the sequential SGD for non-convex problems, and (2) exhibits good scalability due to the linear speedup property with respect to both the number of workers and the average number of local updates. Evaluations show that LOSP significantly improves performance over the state-of-the-art ones in terms of both convergence accuracy and communication cost. [ABSTRACT FROM AUTHOR]

Performing deep neural network (DNN) inference in real time requires excessive network resources, which poses a big challenge to the resource-limited industrial Internet of things (IIoT) networks. To address the challenge, in this paper, we introduce an end-edge-cloud orchestration architecture, in which the inference task assignment and DNN model placement are flexibly coordinated. Specifically, the DNN models, trained and pre-stored in the cloud, are properly placed at the end and edge to perform DNN inference. To achieve efficient DNN inference, a multi-dimensional resource management problem is formulated to maximize the average inference accuracy while satisfying the strict delay requirements of inference tasks. Due to the mix-integer decision variables, it is difficult to solve the formulated problem directly. Thus, we transform the formulated problem into a Markov decision process which can be solved efficiently. Furthermore, a deep reinforcement learning based resource management scheme is proposed to make real-time optimal resource allocation decisions. Simulation results are provided to demonstrate that the proposed scheme can efficiently allocate the available spectrum, caching, and computing resources, and improve average inference accuracy by 31.4 % compared with the deep deterministic policy gradient benchmark. [ABSTRACT FROM AUTHOR]

Breakthroughs in unsupervised domain adaptation (uDA) can help in adapting models from a label-rich source domain to unlabeled target domains. Despite these advancements, there is a lack of research on how uDA algorithms, particularly those based on adversarial learning, can work in distributed settings. In real-world applications, target domains are often distributed across thousands of devices, and existing adversarial uDA algorithms – which are centralized in nature – cannot be applied in these settings. To solve this important problem, we introduce FRuDA: an end-to-end framework for distributed adversarial uDA. Through a careful analysis of the uDA literature, we identify the design goals for a distributed uDA system and propose two novel algorithms to increase adaptation accuracy and training efficiency of adversarial uDA in distributed settings. Our evaluation of FRuDA with five image and speech datasets show that it can boost target domain accuracy by up to 50% and improve the training efficiency of adversarial uDA by at least $11\times$ 11 × . [ABSTRACT FROM AUTHOR]

Power control in massive multiple input multiple output (MIMO) systems is an appealing technique to improve network performance and reliability. The traditional methods to solve such problems are based on the convex optimization theory, which incurs high computational complexity. In contrast, this work leverages deep neural networks to maximize the minimum data rate of the downlink users in the massive MIMO network. Based on the different setups in the practical systems, namely in-distribution case, weakly out-of-distribution case, and out-of-distribution case, we propose three approaches to solve them. Specifically, first, we establish a densely connected neural network for solving the power control problem. Then, for the case where the test data and training data come from the same distributions (the in-distribution case), we use the established neural network to obtain an approximately optimal power control strategy, and propose a self-training-based algorithm to use the unlabeled samples collected in the actual system to further improve the system performance. For the case that the test data and training data come from different distributions and a small amount of labeled target domain data can be obtained (the weakly out-of-distribution case), we propose a pre-training and fine-tuning algorithm to solve the problem. For the issue that we can not obtain the labels of the target domain data (the out-of-distribution case), we transform the problem into a covariate shift problem and propose an algorithm by weighting the loss function. Numerical results demonstrate that the proposed schemes not only match the optimal solution well but also have low online inference complexity. [ABSTRACT FROM AUTHOR]

In this work, we introduce a new concept, named source-free open compound domain adaptation (SF-OCDA), and study it in semantic segmentation. SF-OCDA is more challenging than the traditional domain adaptation but it is more practical. It jointly considers (1) the issues of data privacy and data storage and (2) the scenario of multiple target domains and unseen open domains. In SF-OCDA, only the source pre-trained model and the target data are available to learn the target model. The model is evaluated on the samples from the target and unseen open domains. To solve this problem, we present an effective framework by separating the training process into two stages: (1) pre-training a generalized source model and (2) adapting a target model with self-supervised learning. In our framework, we propose the Cross-Patch Style Swap (CPSS) to diversify samples with various patch styles in the feature-level, which can benefit the training of both stages. First, CPSS can significantly improve the generalization ability of the source model, providing more accurate pseudo-labels for the latter stage. Second, CPSS can reduce the influence of noisy pseudo-labels and also avoid the model overfitting to the target domain during self-supervised learning, consistently boosting the performance on the target and open domains. Experiments demonstrate that our method produces state-of-the-art results on the C-Driving dataset. Furthermore, our model also achieves the leading performance on CityScapes for domain generalization. [ABSTRACT FROM AUTHOR]

Most recent object detection methods have achieved growing performance on public datasets. However, enormous efforts are needed for these methods due to the extensive annotations of ground-truth boxes. Weakly Supervised Object Detection (WSOD) methods hence have been proposed to solve this problem as only image-level annotations are required and then output bounding boxes related to the objects. In order to further elevate the weakly supervised detection methods on the extraction of reasonable features, the training of potential positive proposals, and the generation of proposals before training, we propose a new Combined Backbone and Advanced Selection Heads (CBASH) method with the proposals generated from the object semantic information. Specifically, Combined Backbone will make the unobvious object features more noticeable, Advanced Selection Heads promote more potential positive proposals to get training, and the generated object semantic proposals elevate the quality and quantity of positive proposals. The proposed method is evaluated on the challenging PASCAL VOC 2007 and 2012 benchmark datasets. Experimental results show that our proposed method can achieve improved performance on both VOC 2007 and VOC 2012 datasets and outperforms the existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Image restoration is a long-standing problem in signal processing and low-level computer vision. Previous studies have shown that imposing a low-rank Tucker decomposition (TKD) constraint could produce impressive performances. However, the TKD-based schemes may lead to the overfitting/underfitting problem because of incorrectly predefined ranks. To address this issue, we prove that the $n$ -rank is upper bounded by the rank of each Tucker factor matrix. Using this relationship, we propose a formulation by imposing the nuclear norm regularization on the latent factors of TKD, which can avoid the burden of rank selection and reduce the computational cost when dealing with large-scale tensors. In this formulation, we adopt the Minimax Concave Penalty to remove the impulsive noise instead of the $l_{1}$ -norm which may deviate from both the data-acquisition model and the prior model. Moreover, we employ an anisotropic total variation regularization to explore the piecewise smooth structure in both spatial and spectral domains. To solve this problem, we design the symmetric Gauss-Seidel (sGS) based alternating direction method of multipliers (ADMM) algorithm. Compared to the directly extended ADMM, our algorithm can achieve higher accuracy since more structural information is utilized. Finally, we conduct experiments on the three kinds of datasets, numerical results demonstrate the superiority of the proposed method, especially, the average PSNR of the proposed method can improve about 1~5dB for each noise level of color images. [ABSTRACT FROM AUTHOR]

Unsupervised person re-identification (Re-Id) has attracted increasing attention due to its practical application in the read-world video surveillance system. The traditional unsupervised Re-Id are mostly based on the method alternating between clustering and fine-tuning with the classification or metric learning objectives on the grouped clusters. However, since person Re-Id is an open-set problem, the clustering based methods often leave out lots of outlier instances or group the instances into the wrong clusters, thus they can not make full use of the training samples as a whole. To solve these problems, we present the hybrid dynamic cluster contrast and probability distillation algorithm. It formulates the unsupervised Re-Id problem into an unified local-to-global dynamic contrastive learning and self-supervised probability distillation framework. Specifically, the proposed method can make the best of the self-supervised signals of all the clustered and un-clustered instances, from both the instances’ self-contrastive level and the probability distillation respectives, in the memory-based non-parametric manner. Besides, the proposed hybrid local-to-global contrastive learning can take full advantage of the informative and valuable training examples for effective and robust training. Extensive experiment results show that the proposed method achieves superior performances to state-of-the-art methods, under both the purely unsupervised and unsupervised domain adaptation experiment settings. Our source code is released in https://github.com/zjy2050/HDCRL-ReID. [ABSTRACT FROM AUTHOR]

Ranking paths becomes an increasingly important functionality in many transportation services, where multiple paths connecting a source-destination pair are offered to drivers. We study ranking such paths under specific contexts, e.g., at a departure time and for a specific driver. More specifically, we model ranking as a regression problem where we assign a ranking score to each path with the help of historical trajectories. The intuition is that if a driver’s trajectory used path $P$ P at time $t$ t , we consider this as an evidence that path $P$ P is preferred by the driver at time $t$ t , thus should have a higher ranking score than other paths connecting the same source and destination. To solve the regression problem, we first propose an effective training data enriching method to obtain a compact and diversified set of training paths using historical trajectories, which provides a data foundation for efficient and effective learning. Next, we propose a multi-task learning framework that considers features representing both candidate paths and contexts. Specifically, a road network embedding is proposed to embed paths into feature vectors by considering both road network topology and spatial properties, such as distances and travel times. By modeling different departure times as a temporal graph, graph embedding is used to embed departure times into feature vectors. The objective function not only considers the discrepancies on ranking scores but also the reconstruction errors of the spatial properties of the paths, which in turn improves the final ranking estimation. Empirical studies on a substantial trajectory data set offer insight into the designed properties of the proposed framework, indicating that it is effective and practical in real world settings. [ABSTRACT FROM AUTHOR]

To address the problem of inadequate feature extraction and binary code discrete optimization faced by deep hashing methods using a relaxation-quantization strategy, a novel deep attention-guided hashing method with pairwise labels (DAHP) is proposed to enhance global feature fusion, better learn the contextual information of image features to effectively enhance the feature representation, and solve the problem of losing feature information in discrete optimization by optimizing the loss function. First, we introduce a new concept called the anchor hash code generation(AHCG) algorithm, we train the ResNet with the position attention and channel attention mechanisms with the anchor points in Hamming space as supervised information, we fit the binary code representing the picture to the vicinity of each anchor point, and finally, we use the optimized loss function to calculate the pairwise loss and the anchor loss, allowing the hash function to generate hash code with strong discriminative power. The experiments were conducted on four benchmark datasets, and the retrieval accuracy of the proposed method outperformed the retrieval accuracies of the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In monochrome-color dual-lens systems, the monochrome camera can capture images with higher quality than the color camera. To obtain high quality color images, a better approach is to colorize the gray images from the monochrome camera with the color images from the color camera serving as a reference. In addition, the colorization may fail in some cases, which makes the estimation of the colorization quality a necessary step before outputting the colorization result. To solve these problems, we propose a deep convolutional network based framework. 1) In the colorization module, the proposed colorization CNN uses deep feature representations, attention operation, 3-D regulation and color correction to make use of colors of multiple pixels in the reference image for colorizing each pixel in the input gray image. 2) In the colorization quality estimation module, based on the symmetry property of colorization, we propose to utilize the colorization CNN again to colorize the gray map of the original reference color image using the first-time colorization result from the colorization module as reference. Then, the quality loss of the second-time colorization result can be used for estimating the colorization quality. Experimental results show that our method can largely outperform the state-of-the-art colorization methods and estimate the colorization quality accurately as well. [ABSTRACT FROM AUTHOR]

Federated learning enables local devices to jointly train the server model while keeping the data decentralized and private. In federated learning, all local data should be annotated by alternative labeling techniques since the annotator in the server cannot access the data. Therefore, it is hardly guaranteed that they are correctly annotated. Under this noisy label setting, local models form inconsistent class decision boundaries with one another, and their weights severely diverge, which are serious problems in federated learning. To solve these problems, we introduce a novel federated learning scheme that allows the server to cooperate with local models by interchanging class-wise centroids. The server aligns the class-wise centroids, which are central features of local data on each device, and broadcasts aligned centroids to selected clients every communication round. Updating local models with the aligned centroids helps us to form consistent class decision boundaries among local models, although the noise distributions in clients' data are different from each other. Furthermore, we introduce a sample selection approach to filter out data with noisy labels and a label correction method to adjust the labels of noisy instances. Our experimental results show that our approach is noticeably effective in federated learning with noisy labels. [ABSTRACT FROM AUTHOR]

In the field of unsupervised person Re-identification (Re-ID), mainstream methods adopt cluster algorithm to generate pseudo labels for training. Despite the effectiveness, the cluster algorithm generates noisy labels, which are retained in further model updating and hinder higher performance. To solve this problem, we propose a Two-branch Asymmetric Model with Alternately Clustering. Specifically, the designed Alternately Clustering (AC) strategy leverages a two-branch model to cluster different pseudo labels for each branch, which prevents the continuous existence of identical noisy labels. To establish a mapping between the two label sets, pseudo label mapping constraint (PLMC) module is devised, which helps retain reliable pseudo labels. Our method improves the quality of generated pseudo labels by keeping noisy labels changing and retaining the reliable ones. Experimental results demonstrate that our proposed method outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

AC optimal power flow (AC-OPF) problems need to be solved more frequently in the future to maintain stable and economic power system operation. To tackle this challenge, a deep neural network-based voltage-constrained approach (DeepOPF-V) is proposed to solve AC-OPF problems with high computational efficiency. Its unique design predicts voltages of all buses and then uses them to reconstruct the remaining variables without solving non-linear AC power flow equations. A fast post-processing process is also developed to enforce the box constraints. The effectiveness of DeepOPF-V is validated by simulations on IEEE 118/300-bus systems and a 2000-bus test system. Compared with existing studies, DeepOPF-V achieves decent computation speedup up to four orders of magnitude and comparable performance in optimality gap, while preserving feasibility of the solution. [ABSTRACT FROM AUTHOR]

We consider the problem of max-min power control for downlink cell-free (CF) massive MIMO systems. Under the bisection framework, solving this problem amounts to solving a sequence of convex conic feasibility checking problems (CCFCP). Unfortunately, the problem size of the CCFCP of the CF massive MIMO system grows rapidly as the number of users and access points (AP) increases. Existing feasibility checking methods become computationally intractable even when the system consists of only a moderate number of users and APs. To address this limitation, we propose to reformulate the CCFCP as a two-set feasibility problem, which is then solved by the averaged alternating reflection (AAR) algorithm. The proposed method outperforms existing methods significantly in terms of computational efficiency. [ABSTRACT FROM AUTHOR]

The synthesis of a metasurface exhibiting a specific set of desired scattering properties is a time-consuming and resource-demanding process, which conventionally relies on many cycles of full-wave simulations. It requires an experienced designer to choose the number of metallic layers, the scatterer shapes and dimensions, and the type and the thickness of the separating substrates. In this article, we propose a generative machine learning (ML)-based approach to solve this one-to-many mapping and automate the inverse design of dual- and triple-layer metasurfaces. Using this approach, it is possible to solve optimization problems with single or more constraints by synthesizing thin structures composed of potentially brand-new scatterer designs, in cases where the interlayer coupling between the layers is nonnegligible and synthesis by traditional methods becomes cumbersome. Various examples to provide specific magnitude and phase responses of $x$ - and $y$ -polarized scattering coefficients across a frequency range as well as bounded responses for different metasurface applications are presented to verify the practicality of the proposed method. [ABSTRACT FROM AUTHOR]

Detecting the defects of the semiconductor devices produced using manufacturing processes is essential for quality assurance, and it requires the acquisition and accurate classification of high-resolution scanning electron microscopy images. However, owing to the difficulty of automation, the classification process is costly, and its efficiency must also be improved. To improve the classification accuracy and reduce the cost of classifiers, which are the main bottlenecks of conventional technology, we proposed a deep convolutional neural network (CNN) based on the VGG16 architecture and performed appropriate data augmentations on training images. Reducing training images is an effective method for reducing the cost of creating classifiers. However, in this case, the classification accuracy is insufficient, as it greatly varies depending on the number of training images. The appropriate data augmentation of training images is an effective method for solving this problem. It was important to note that improper data augmentation reduces the classification accuracy. Also, we managed to find the optimal data augmentation type for a possible defect type. [ABSTRACT FROM AUTHOR]

The adaptive traffic signal control (ATSC) problem can be modeled as a multiagent cooperative game among urban intersections, where intersections cooperate to counter the city's traffic conditions. Recently, reinforcement learning (RL) has achieved marked successes in managing sequential decision making problems, which motivates us to apply RL in the ATSC problem. One of the largest challenges of this problem is that the observation of intersection is typically partially observable, which limits the learning performance of RL algorithms. Considering the large scale of intersections in an urban traffic environment, we use independent RL to solve ATSC problem in this study. We model ATSC problem as a partially observable weak cooperative traffic model (PO-WCTM). Different from a traditional IRL task that averages the returns of all agents in fully cooperative games, the learning goal of each intersection in PO-WCTM is to reduce the cooperative difficulty of learning, which is also consistent with the traffic environment hypothesis. To achieve the optimal cooperative strategy of PO-WCTM, we propose an IRL algorithm called Cooperative Important Lenient Double DQN (CIL-DDQN), which extends Double DQN (DDQN) algorithm using two mechanisms: the forgetful experience mechanism and the lenient weight training mechanism. The former mechanism decreases the importance of experiences stored in the experience reply buffers, while the latter mechanism increases the weight experiences with high estimation and ‘leniently’ trains the DDQN neural network. Experiments in two real traffic scenarios and one simulated traffic scenarios show that, CIL-DDQN outperforms other methods in almost all performance indicators of ATSC. [ABSTRACT FROM AUTHOR]

In recent decades, deep learning (DL) has become a rapidly growing research direction, redefining the state-of-the-art performances in a wide range of techniques, such as object detection and speech recognition. In the aircraft design, dynamics, and control field, many works hinge on the information-rich data-driven approach, which includes the fusion-based prognostic and health management, the airliner's flight safety monitoring, intelligent sensing, and flight control systems development. While DL provides great potentials to solve these data-driven problems, a systematic review and discussion as to how the DL has been/can be used for these problems are still missing in relation to the rapidly developing and widely used DL techniques. In this article, we aim to address this urgent issue to provide a timely overview of the state-of-the-art for applying DL to the aircraft design, dynamics, and control field. In particular, we briefly introduce five representative DL methods, i.e., deep neural network, deep autoencoder, deep belief network, convolutional neural network, and recurrent neural network. Mathematical definitions for each method are presented, and illustrative applications are also discussed. We then review the existing DL-based works that have appeared in the aircraft design, dynamics, and control field. The review efforts are divided into two major groups, i.e., the own-ship aircraft modeling, wherein the works have been/can be implemented online for the aircraft design/dynamics/control, and other airplanes research works, wherein DL-based schemes provide offline monitoring of the aircraft operation. We then summarize the data sources and DL architectures. Referring to the experiences of DL research works/techniques development in other related fields, future opportunities, challenges, and potential solutions for implementing DL in the aircraft design, dynamics, and control field are also discussed. [ABSTRACT FROM AUTHOR]