Search

In deep face recognition, the commonly used softmax loss and its newly proposed variations are not yet sufficiently effective to handle the class imbalance and softmax saturation issues during the training process while extracting discriminative features. In this brief, to address both issues, we propose a class-variant margin (CVM) normalized softmax loss, by introducing a true-class margin and a false-class margin into the cosine space of the angle between the feature vector and the class-weight vector. The true-class margin alleviates the class imbalance problem, and the false-class margin postpones the early individual saturation of softmax. With negligible computational complexity increment during training, the new loss function is easy to implement in the common deep learning frameworks. Comprehensive experiments on the LFW, YTF, and MegaFace protocols demonstrate the effectiveness of the proposed CVM loss function.

Existing deep learning-based facial attribute recognition (FAR) methods rely heavily on large-scale labeled training data. Unfortunately, in many real-world applications, only limited labeled data are available, resulting in the performance deterioration of these methods. To address this issue, we propose a novel spatial-semantic patch learning network (SPL-Net), consisting of a multi-branch shared subnetwork (MSS), three auxiliary task subnetworks (ATS), and an FAR subnetwork, for attribute classification with limited labeled data. Considering the diversity of facial attributes, MSS includes a task-shared branch and four region branches, each of which contains cascaded dual cross attention modules to extract region-specific features. SPL-Net involves a two-stage learning procedure. In the first stage, MSS and ATS are jointly trained to perform three auxiliary tasks (i.e., a patch rotation task (PRT), a patch segmentation task (PST), and a patch classification task (PCT)), which exploit the spatial-semantic relationship on large-scale unlabeled facial data from various perspectives. Specifically, PRT encodes the spatial information of facial images based on self-supervised learning. PST and PCT respectively capture the pixel-level and image-level semantic information of facial images by leveraging a facial parsing model. Thus, a well-pretrained MSS is obtained. In the second stage, based on the pre-trained MSS, an FAR model is easily fine-tuned to predict facial attributes by requiring only a small amount of labeled data. Experimental results on challenging facial attribute datasets (including CelebA, LFWA, and MAAD) show the superiority of SPL-Net over several state-of-the-art methods in the case of limited labeled data. [ABSTRACT FROM AUTHOR]

Over the past few years, deep convolutional neural network-based methods have made great progress in semantic segmentation of street scenes. Some recent methods align feature maps to alleviate the semantic gap between them and achieve high segmentation accuracy. However, they usually adopt the feature alignment modules with the same network configuration in the decoder and thus ignore the different roles of stages of the decoder during feature aggregation, leading to a complex decoder structure. Such a manner greatly affects the inference speed. In this paper, we present a novel Stage-aware Feature Alignment Network (SFANet) based on the encoder-decoder structure for real-time semantic segmentation of street scenes. Specifically, a Stage-aware Feature Alignment module (SFA) is proposed to align and aggregate two adjacent levels of feature maps effectively. In the SFA, by taking into account the unique role of each stage in the decoder, a novel stage-aware Feature Enhancement Block (FEB) is designed to enhance spatial details and contextual information of feature maps from the encoder. In this way, we are able to address the misalignment problem with a very simple and efficient multi-branch decoder structure. Moreover, an auxiliary training strategy is developed to explicitly alleviate the multi-scale object problem without bringing additional computational costs during the inference phase. Experimental results show that the proposed SFANet exhibits a good balance between accuracy and speed for real-time semantic segmentation of street scenes. In particular, based on ResNet-18, SFANet respectively obtains 78.1% and 74.7% mean of class-wise Intersection-over-Union (mIoU) at inference speeds of 37 FPS and 96 FPS on the challenging Cityscapes and CamVid test datasets by using only a single GTX 1080Ti GPU. [ABSTRACT FROM AUTHOR]

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

Lane marking detection is a fundamental but crucial step in intelligent driving systems. It can not only provide relevant road condition information to prevent lane departure but also assist vehicle positioning and forehead car detection. However, lane marking detection faces many challenges, including extreme lighting, missing lane markings, and obstacle obstructions. Recently, deep learning-based algorithms draw much attention in intelligent driving society because of their excellent performance. In this paper, we review deep learning methods for lane marking detection, focusing on their network structures and optimization objectives, the two key determinants of their success. Besides, we summarize existing lane-related datasets, evaluation criteria, and common data processing techniques. We also compare the detection performance and running time of various methods, and conclude with some current challenges and future trends for deep learning-based lane marking detection algorithm. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel adaptive deep disturbance-disentangled learning (ADDL) method for effective facial expression recognition (FER). ADDL involves a two-stage learning procedure. First, a disturbance feature extraction model is trained to identify multiple disturbing factors on a large-scale face database involving disturbance label information. Second, an adaptive disturbance-disentangled model, which contains a global shared subnetwork and two task-specific subnetworks, is designed and learned to explicitly disentangle disturbing factors from facial expression images. In particular, the expression subnetwork leverages a multi-level attention mechanism to extract expression-specific features, while the disturbance subnetwork embraces a new adaptive disturbance feature learning module to extract disturbance-specific features based on adversarial transfer learning. Moreover, a mutual information neural estimator is adopted to minimize the correlation between expression-specific and disturbance-specific features. Extensive experimental results on both in-the-lab FER databases (including CK+, MMI, and Oulu-CASIA) and in-the-wild FER databases (including RAF-DB, SFEW, Aff-Wild2, and AffectNet) show that our proposed method consistently outperforms several state-of-the-art FER methods. This clearly demonstrates the great potential of disturbance disentanglement for FER. Our code is available at https://github.com/delian11/ADDL. [ABSTRACT FROM AUTHOR]

In recent years, deep learning-based person re-identification (Re-ID) methods have made significant progress. However, the performance of these methods substantially decreases when dealing with occlusion, which is ubiquitous in realistic scenarios. In this article, we propose a novel semantic-aware occlusion-robust network (SORN) that effectively exploits the intrinsic relationship between the tasks of person Re-ID and semantic segmentation for occluded person Re-ID. Specifically, the SORN is composed of three branches, including a local branch, a global branch, and a semantic branch. In particular, the local branch extracts part-based local features, and the global branch leverages a novel spatial-patch contrastive loss (SPC) to extract occlusion-robust global features. Meanwhile, the semantic branch generates a foreground-background mask for a pedestrian image, which indicates the non-occluded areas of the human body. The three branches are jointly trained in a unified multi-task learning network. Finally, pedestrian matching is performed based on the local features extracted from the non-occluded areas and the global features extracted from the whole pedestrian image. Extensive experimental results on a large-scale occluded person Re-ID dataset (i.e., Occluded-DukeMTMC) and two partial person Re-ID datasets (i.e., Partial-REID and Partial-iLIDS) show the superiority of the proposed method compared with several state-of-the-art methods for occluded and partial person Re-ID. We also demonstrate the effectiveness of the proposed method on two general person Re-ID datasets (i.e., Market-1501 and DukeMTMC-reID). [ABSTRACT FROM AUTHOR]

Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep networks under small sample sizes, learning discriminative features is crucial. To this end, several loss functions have been proposed to encourage large intra-class compactness and inter-class separability. In this paper, we propose to enhance the discriminative power of features from a new perspective by introducing a novel neural network termed Relation-and-Margin learning Network (ReMarNet). Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms. Specifically, a relation network is used to learn the features that can support classification based on the similarity between a sample and a class prototype; at the meantime, a fully connected network with the cross entropy loss is used for classification via the decision boundary. Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples and achieves competitive performance against state-of-the-art methods. Code is available at https://github.com/liyunyu08/ReMarNet. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new loss function, termed the equalized margin (EqM) loss, which is designed to make both intra-class scopes and inter-class margins similar over all classes, such that all the classes can be evenly distributed on the hypersphere of the feature space. The EqM loss controls both the lower limit of intra-class similarity by exploiting hard-sample mining and the upper limit of inter-class similarity by assuring equalized margins. Therefore, using the EqM loss, we can not only obtain more discriminative features, but also overcome the negative impacts from the data imbalance on the inter-class margins. We also observe that the EqM loss is stable with the variation of the scale in normalized Softmax. Furthermore, by conducting extensive experiments on LFW, YTF, CFP, MegaFace and IJB-B, we are able to verify the effectiveness and superiority of the EqM loss, compared with other state-of-the-art loss functions for face recognition. [ABSTRACT FROM AUTHOR]

A deep neural network of multiple nonlinear layers forms a large function space, which can easily lead to overfitting when it encounters small-sample data. To mitigate overfitting in small-sample classification, learning more discriminative features from small-sample data is becoming a new trend. To this end, this paper aims to find a subspace of neural networks that can facilitate a large decision margin. Specifically, we propose the Orthogonal Softmax Layer (OSL), which makes the weight vectors in the classification layer remain orthogonal during both the training and test processes. The Rademacher complexity of a network using the OSL is only $\frac {1}{K}$ , where $K$ is the number of classes, of that of a network using the fully connected classification layer, leading to a tighter generalization error bound. Experimental results demonstrate that the proposed OSL has better performance than the methods used for comparison on four small-sample benchmark datasets, as well as its applicability to large-sample datasets. Codes are available at: https://github.com/dongliangchang/OSLNet. [ABSTRACT FROM AUTHOR]

Single image super-resolution (SISR) is a notoriously challenging ill-posed problem that aims to obtain a high-resolution output from one of its low-resolution versions. Recently, powerful deep learning algorithms have been applied to SISR and have achieved state-of-the-art performance. In this survey, we review representative deep learning-based SISR methods and group them into two categories according to their contributions to two essential aspects of SISR: The exploration of efficient neural network architectures for SISR and the development of effective optimization objectives for deep SISR learning. For each category, a baseline is first established, and several critical limitations of the baseline are summarized. Then, representative works on overcoming these limitations are presented based on their original content, as well as our critical exposition and analyses, and relevant comparisons are conducted from a variety of perspectives. Finally, we conclude this review with some current challenges and future trends in SISR that leverage deep learning algorithms. [ABSTRACT FROM AUTHOR]

• We propose ReNAP for few-shot classification. • The APL module of ReNAP can learn class prototypes adaptively. • Experimental results demonstrate the superior classification performance of ReNAP. Traditional deep learning-based image classification methods often fail to recognize a new class that does not exist in the training dataset, particularly when the new class only has a small number of samples. Such a challenging and new learning problem is referred to as few-shot learning. In few-shot learning, the relation network (RelationNet) is a powerful method. However, in RelationNet and its state-of-the-art variants, the prototype of each class is obtained by a simple summation or average over the labeled samples. These simple sample statistics cannot accurately capture the distinct characteristics of the diverse classes of real-world images. To address this problem, in this paper, we propose the Relation Network with Adaptive Prototypical Learning method (ReNAP), which can learn the class prototypes adaptively and provide more accurate representations of the classes. More specifically, ReNAP embeds an adaptive prototypical learning module constructed by a convolutional network into RelationNet. Our ReNAP achieves superior classification performances to RelationNet and other state-of-the-art methods on four widely used benchmark datasets, FC100, CUB-200-2011, Stanford-Cars, and Stanford-Dogs. [ABSTRACT FROM AUTHOR]

Automatic speech recognition (ASR) is a crucial technology for man-machine interaction. End-to-end models have been studied recently in deep learning for ASR. However, these models are not suitable for the practical application of ASR due to their large model sizes and computation costs. To address this issue, we propose a novel mutual-learning sequence-level knowledge distillation framework enjoying distinct student structures for ASR. Trained mutually and simultaneously, each student learns not only from the pre-trained teacher but also from its distinct peers, which can improve the generalization capability of the whole network, through making up for the insufficiency of each student and bridging the gap between each student and the teacher. Extensive experiments on the TIMIT and large LibriSpeech corpuses show that, compared with the state-of-the-art methods, the proposed method achieves an excellent balance between recognition accuracy and model compression. [ABSTRACT FROM AUTHOR]

• A novel large and realistic multi-focus dataset with ground truth is constructed. • The proposed dataset can serve as a test bench for multi-focus image fusion methods. • Benefit future development of deep-learning-based methods for multi-focus image fusion. Multi-focus image fusion, a technique to generate an all-in-focus image from two or more partially-focused source images, can benefit many computer vision tasks. However, currently there is no large and realistic dataset to perform convincing evaluation and comparison of algorithms in multi-focus image fusion. Moreover, it is difficult to train a deep neural network for multi-focus image fusion without a suitable dataset. In this letter, we introduce a large and realistic multi-focus dataset called Real-MFF, which contains 710 pairs of source images with corresponding ground truth images. The dataset is generated by light field images, and both the source images and the ground truth images are realistic. To serve as both a well-established benchmark for existing multi-focus image fusion algorithms and an appropriate training dataset for future development of deep-learning-based methods, the dataset contains a variety of scenes, including buildings, plants, humans, shopping malls, squares and so on. We also evaluate 10 typical multi-focus algorithms on this dataset for the purpose of illustration. [ABSTRACT FROM AUTHOR]

• A detailed review of latest deep metric learning methods for few-shot image classification. • More than 60 methods published from 2018 to 2022 are surveyed. • Methods are divided according to three stages of deep metric learning. • Challenges and future directions of few-shot image classification are discussed. Few-shot image classification is a challenging problem that aims to achieve the human level of recognition based only on a small number of training images. One main solution to few-shot image classification is deep metric learning. These methods, by classifying unseen samples according to their distances to few seen samples in an embedding space learned by powerful deep neural networks, can avoid overfitting to few training images in few-shot image classification and have achieved the state-of-the-art performance. In this paper, we provide an up-to-date review of deep metric learning methods for few-shot image classification from 2018 to 2022 and categorize them into three groups according to three stages of metric learning, namely learning feature embeddings, learning class representations, and learning distance measures. Under this taxonomy, we identify the trends of transitioning from learning task-agnostic features to task-specific features, from simple computation of prototypes to computing task-dependent prototypes or learning prototypes, from using analytical distance or similarity measures to learning similarities through convolutional or graph neural networks. Finally, we discuss the current challenges and future directions of few-shot deep metric learning from the perspectives of effectiveness, optimization and applicability, and summarize their applications to real-world computer vision tasks. [ABSTRACT FROM AUTHOR]