Dan Zeng

Gongyang Li, Zhi Liu, Dan Zeng et al.

Salient object detection (SOD) in optical remote sensing images (RSIs), or RSI-SOD, is an emerging topic in understanding optical RSIs. However, due to the difference between optical RSIs and natural scene images (NSIs), directly applying NSI-SOD methods to optical RSIs fails to achieve satisfactory results. In this paper, we propose a novel Adjacent Context Coordination Network (ACCoNet) to explore the coordination of adjacent features in an encoder-decoder architecture for RSI-SOD. Specifically, ACCoNet consists of three parts: an encoder, Adjacent Context Coordination Modules (ACCoMs), and a decoder. As the key component of ACCoNet, ACCoM activates the salient regions of output features of the encoder and transmits them to the decoder. ACCoM contains a local branch and two adjacent branches to coordinate the multi-level features simultaneously. The local branch highlights the salient regions in an adaptive way, while the adjacent branches introduce global information of adjacent levels to enhance salient regions. Additionally, to extend the capabilities of the classic decoder block (i.e., several cascaded convolutional layers), we extend it with two bifurcations and propose a Bifurcation-Aggregation Block to capture the contextual information in the decoder. Extensive experiments on two benchmark datasets demonstrate that the proposed ACCoNet outperforms 22 state-of-the-art methods under nine evaluation metrics, and runs up to 81 fps on a single NVIDIA Titan X GPU. The code and results of our method are available at https://github.com/MathLee/ACCoNet.

Hui Zhang, Zheng Wang, Dan Zeng et al.

Anomaly detection has garnered extensive applications in real industrial manufacturing due to its remarkable effectiveness and efficiency. However, previous generative-based models have been limited by suboptimal reconstruction quality, hampering their overall performance. We introduce DiffusionAD, a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network. A fundamental enhancement lies in our reformulation of the reconstruction process using a diffusion model into a noise-to-norm paradigm. Here, the anomalous region loses its distinctive features after being disturbed by Gaussian noise and is subsequently reconstructed into an anomaly-free one. Afterward, the segmentation sub-network predicts pixel-level anomaly scores based on the similarities and discrepancies between the input image and its anomaly-free reconstruction. Additionally, given the substantial decrease in inference speed due to the iterative denoising nature of diffusion models, we revisit the denoising process and introduce a rapid one-step denoising paradigm. This paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality. Furthermore, considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales, enhancing the fidelity of reconstructions. Comprehensive evaluations on four standard and challenging benchmarks reveal that DiffusionAD outperforms current state-of-the-art approaches and achieves comparable inference speed, demonstrating the effectiveness and broad applicability of the proposed pipeline. Code is released at https://github.com/HuiZhang0812/DiffusionAD

Shikun Li, Tongliang Liu, Jiyong Tan et al.

Supervised deep learning depends on massive accurately annotated examples, which is usually impractical in many real-world scenarios. A typical alternative is learning from multiple noisy annotators. Numerous earlier works assume that all labels are noisy, while it is usually the case that a few trusted samples with clean labels are available. This raises the following important question: how can we effectively use a small amount of trusted data to facilitate robust classifier learning from multiple annotators? This paper proposes a data-efficient approach, called \emph{Trustable Co-label Learning} (TCL), to learn deep classifiers from multiple noisy annotators when a small set of trusted data is available. This approach follows the coupled-view learning manner, which jointly learns the data classifier and the label aggregator. It effectively uses trusted data as a guide to generate trustable soft labels (termed co-labels). A co-label learning can then be performed by alternately reannotating the pseudo labels and refining the classifiers. In addition, we further improve TCL for a special complete data case, where each instance is labeled by all annotators and the label aggregator is represented by multilayer neural networks to enhance model capacity. Extensive experiments on synthetic and real datasets clearly demonstrate the effectiveness and robustness of the proposed approach. Source code is available at https://github.com/ShikunLi/TCL

Gongyang Li, Yike Wang, Zhi Liu et al.

Semantic segmentation is important for scene understanding. To address the scenes of adverse illumination conditions of natural images, thermal infrared (TIR) images are introduced. Most existing RGB-T semantic segmentation methods follow three cross-modal fusion paradigms, i.e. encoder fusion, decoder fusion, and feature fusion. Some methods, unfortunately, ignore the properties of RGB and TIR features or the properties of features at different levels. In this paper, we propose a novel feature fusion-based network for RGB-T semantic segmentation, named \emph{LASNet}, which follows three steps of location, activation, and sharpening. The highlight of LASNet is that we fully consider the characteristics of cross-modal features at different levels, and accordingly propose three specific modules for better segmentation. Concretely, we propose a Collaborative Location Module (CLM) for high-level semantic features, aiming to locate all potential objects. We propose a Complementary Activation Module for middle-level features, aiming to activate exact regions of different objects. We propose an Edge Sharpening Module (ESM) for low-level texture features, aiming to sharpen the edges of objects. Furthermore, in the training phase, we attach a location supervision and an edge supervision after CLM and ESM, respectively, and impose two semantic supervisions in the decoder part to facilitate network convergence. Experimental results on two public datasets demonstrate that the superiority of our LASNet over relevant state-of-the-art methods. The code and results of our method are available at https://github.com/MathLee/LASNet.

Xiao Wang, Yuhang Huang, Dan Zeng et al.

As a representative self-supervised method, contrastive learning has achieved great successes in unsupervised training of representations. It trains an encoder by distinguishing positive samples from negative ones given query anchors. These positive and negative samples play critical roles in defining the objective to learn the discriminative encoder, avoiding it from learning trivial features. While existing methods heuristically choose these samples, we present a principled method where both positive and negative samples are directly learnable end-to-end with the encoder. We show that the positive and negative samples can be cooperatively and adversarially learned by minimizing and maximizing the contrastive loss, respectively. This yields cooperative positives and adversarial negatives with respect to the encoder, which are updated to continuously track the learned representation of the query anchors over mini-batches. The proposed method achieves 71.3% and 75.3% in top-1 accuracy respectively over 200 and 800 epochs of pre-training ResNet-50 backbone on ImageNet1K without tricks such as multi-crop or stronger augmentations. With Multi-Crop, it can be further boosted into 75.7%. The source code and pre-trained model are released in https://github.com/maple-research-lab/caco.

Qichao Ying, Xiaoxiao Hu, Yangming Zhou et al.

Previous researches on multimedia fake news detection include a series of complex feature extraction and fusion networks to gather useful information from the news. However, how cross-modal consistency relates to the fidelity of news and how features from different modalities affect the decision-making are still open questions. This paper presents a novel scheme of Bootstrapping Multi-view Representations (BMR) for fake news detection. Given a multi-modal news, we extract representations respectively from the views of the text, the image pattern and the image semantics. Improved Multi-gate Mixture-of-Expert networks (iMMoE) are proposed for feature refinement and fusion. Representations from each view are separately used to coarsely predict the fidelity of the whole news, and the multimodal representations are able to predict the cross-modal consistency. With the prediction scores, we reweigh each view of the representations and bootstrap them for fake news detection. Extensive experiments conducted on typical fake news detection datasets prove that the proposed BMR outperforms state-of-the-art schemes.

Xucheng Wang, Dan Zeng, Qijun Zhao et al.

Unmanned aerial vehicle (UAV) tracking has wide potential applications in such as agriculture, navigation, and public security. However, the limitations of computing resources, battery capacity, and maximum load of UAV hinder the deployment of deep learning-based tracking algorithms on UAV. Consequently, discriminative correlation filters (DCF) trackers stand out in the UAV tracking community because of their high efficiency. However, their precision is usually much lower than trackers based on deep learning. Model compression is a promising way to narrow the gap (i.e., effciency, precision) between DCF- and deep learning- based trackers, which has not caught much attention in UAV tracking. In this paper, we propose the P-SiamFC++ tracker, which is the first to use rank-based filter pruning to compress the SiamFC++ model, achieving a remarkable balance between efficiency and precision. Our method is general and may encourage further studies on UAV tracking with model compression. Extensive experiments on four UAV benchmarks, including UAV123@10fps, DTB70, UAVDT and Vistrone2018, show that P-SiamFC++ tracker significantly outperforms state-of-the-art UAV tracking methods.

You Wu, Xucheng Wang, Dan Zeng et al.

Unmanned aerial vehicle (UAV) tracking is critical for applications like surveillance, search-and-rescue, and autonomous navigation. However, the high-speed movement of UAVs and targets introduces unique challenges, including real-time processing demands and severe motion blur, which degrade the performance of existing generic trackers. While single-stream vision transformer (ViT) architectures have shown promise in visual tracking, their computational inefficiency and lack of UAV-specific optimizations limit their practicality in this domain. In this paper, we boost the efficiency of this framework by tailoring it into an adaptive computation framework that dynamically exits Transformer blocks for real-time UAV tracking. The motivation behind this is that tracking tasks with fewer challenges can be adequately addressed using low-level feature representations. Simpler tasks can often be handled with less demanding, lower-level features. This approach allows the model use computational resources more efficiently by focusing on complex tasks and conserving resources for easier ones. Another significant enhancement introduced in this paper is the improved effectiveness of ViTs in handling motion blur, a common issue in UAV tracking caused by the fast movements of either the UAV, the tracked objects, or both. This is achieved by acquiring motion blur robust representations through enforcing invariance in the feature representation of the target with respect to simulated motion blur. We refer to our proposed approach as BDTrack. Extensive experiments conducted on four tracking benchmarks validate the effectiveness and versatility of our approach, demonstrating its potential as a practical and effective approach for real-time UAV tracking. Code is released at: https://github.com/wuyou3474/BDTrack.

Daichi Zhang, Fanzhao Lin, Yingying Hua et al.

While the abuse of deepfake technology has caused serious concerns recently, how to detect deepfake videos is still a challenge due to the high photo-realistic synthesis of each frame. Existing image-level approaches often focus on single frame and ignore the spatiotemporal cues hidden in deepfake videos, resulting in poor generalization and robustness. The key of a video-level detector is to fully exploit the spatiotemporal inconsistency distributed in local facial regions across different frames in deepfake videos. Inspired by that, this paper proposes a simple yet effective patch-level approach to facilitate deepfake video detection via spatiotemporal dropout transformer. The approach reorganizes each input video into bag of patches that is then fed into a vision transformer to achieve robust representation. Specifically, a spatiotemporal dropout operation is proposed to fully explore patch-level spatiotemporal cues and serve as effective data augmentation to further enhance model's robustness and generalization ability. The operation is flexible and can be easily plugged into existing vision transformers. Extensive experiments demonstrate the effectiveness of our approach against 25 state-of-the-arts with impressive robustness, generalizability, and representation ability.

Shiming Ge, Bochao Liu, Pengju Wang et al.

While deep models have proved successful in learning rich knowledge from massive well-annotated data, they may pose a privacy leakage risk in practical deployment. It is necessary to find an effective trade-off between high utility and strong privacy. In this work, we propose a discriminative-generative distillation approach to learn privacy-preserving deep models. Our key idea is taking models as bridge to distill knowledge from private data and then transfer it to learn a student network via two streams. First, discriminative stream trains a baseline classifier on private data and an ensemble of teachers on multiple disjoint private subsets, respectively. Then, generative stream takes the classifier as a fixed discriminator and trains a generator in a data-free manner. After that, the generator is used to generate massive synthetic data which are further applied to train a variational autoencoder (VAE). Among these synthetic data, a few of them are fed into the teacher ensemble to query labels via differentially private aggregation, while most of them are embedded to the trained VAE for reconstructing synthetic data. Finally, a semi-supervised student learning is performed to simultaneously handle two tasks: knowledge transfer from the teachers with distillation on few privately labeled synthetic data, and knowledge enhancement with tangent-normal adversarial regularization on many triples of reconstructed synthetic data. In this way, our approach can control query cost over private data and mitigate accuracy degradation in a unified manner, leading to a privacy-preserving student model. Extensive experiments and analysis clearly show the effectiveness of the proposed approach.

Dan Zeng, Mingliang Zou, Xucheng Wang et al.

Maintaining high efficiency and high precision are two fundamental challenges in UAV tracking due to the constraints of computing resources, battery capacity, and UAV maximum load. Discriminative correlation filters (DCF)-based trackers can yield high efficiency on a single CPU but with inferior precision. Lightweight Deep learning (DL)-based trackers can achieve a good balance between efficiency and precision but performance gains are limited by the compression rate. High compression rate often leads to poor discriminative representations. To this end, this paper aims to enhance the discriminative power of feature representations from a new feature-learning perspective. Specifically, we attempt to learn more disciminative representations with contrastive instances for UAV tracking in a simple yet effective manner, which not only requires no manual annotations but also allows for developing and deploying a lightweight model. We are the first to explore contrastive learning for UAV tracking. Extensive experiments on four UAV benchmarks, including UAV123@10fps, DTB70, UAVDT and VisDrone2018, show that the proposed DRCI tracker significantly outperforms state-of-the-art UAV tracking methods.

Kangkai Zhang, Shiming Ge, Ruixin Shi et al.

Recognizing objects in low-resolution images is a challenging task due to the lack of informative details. Recent studies have shown that knowledge distillation approaches can effectively transfer knowledge from a high-resolution teacher model to a low-resolution student model by aligning cross-resolution representations. However, these approaches still face limitations in adapting to the situation where the recognized objects exhibit significant representation discrepancies between training and testing images. In this study, we propose a cross-resolution relational contrastive distillation approach to facilitate low-resolution object recognition. Our approach enables the student model to mimic the behavior of a well-trained teacher model which delivers high accuracy in identifying high-resolution objects. To extract sufficient knowledge, the student learning is supervised with contrastive relational distillation loss, which preserves the similarities in various relational structures in contrastive representation space. In this manner, the capability of recovering missing details of familiar low-resolution objects can be effectively enhanced, leading to a better knowledge transfer. Extensive experiments on low-resolution object classification and low-resolution face recognition clearly demonstrate the effectiveness and adaptability of our approach.

Bochao Liu, Jianghu Lu, Pengju Wang et al.

Deep learning models can achieve high inference accuracy by extracting rich knowledge from massive well-annotated data, but may pose the risk of data privacy leakage in practical deployment. In this paper, we present an effective teacher-student learning approach to train privacy-preserving deep learning models via differentially private data-free distillation. The main idea is generating synthetic data to learn a student that can mimic the ability of a teacher well-trained on private data. In the approach, a generator is first pretrained in a data-free manner by incorporating the teacher as a fixed discriminator. With the generator, massive synthetic data can be generated for model training without exposing data privacy. Then, the synthetic data is fed into the teacher to generate private labels. Towards this end, we propose a label differential privacy algorithm termed selective randomized response to protect the label information. Finally, a student is trained on the synthetic data with the supervision of private labels. In this way, both data privacy and label privacy are well protected in a unified framework, leading to privacy-preserving models. Extensive experiments and analysis clearly demonstrate the effectiveness of our approach.

Yan Hu, Zhongxi Qiu, Dan Zeng et al.

Vascular segmentation extracts blood vessels from images and serves as the basis for diagnosing various diseases, like ophthalmic diseases. Ophthalmologists often require high-resolution segmentation results for analysis, which leads to super-computational load by most existing methods. If based on low-resolution input, they easily ignore tiny vessels or cause discontinuity of segmented vessels. To solve these problems, the paper proposes an algorithm named SuperVessel, which gives out high-resolution and accurate vessel segmentation using low-resolution images as input. We first take super-resolution as our auxiliary branch to provide potential high-resolution detail features, which can be deleted in the test phase. Secondly, we propose two modules to enhance the features of the interested segmentation region, including an upsampling with feature decomposition (UFD) module and a feature interaction module (FIM) with a constraining loss to focus on the interested features. Extensive experiments on three publicly available datasets demonstrate that our proposed SuperVessel can segment more tiny vessels with higher segmentation accuracy IoU over 6%, compared with other state-of-the-art algorithms. Besides, the stability of SuperVessel is also stronger than other algorithms. We will release the code after the paper is published.

Hailin Shi, Hang Du, Yibo Hu et al.

Human face images usually appear with wide range of visual scales. The existing face representations pursue the bandwidth of handling scale variation via multi-scale scheme that assembles a finite series of predefined scales. Such multi-shot scheme brings inference burden, and the predefined scales inevitably have gap from real data. Instead, learning scale parameters from data, and using them for one-shot feature inference, is a decent solution. To this end, we reform the conv layer by resorting to the scale-space theory, and achieve two-fold facilities: 1) the conv layer learns a set of scales from real data distribution, each of which is fulfilled by a conv kernel; 2) the layer automatically highlights the feature at the proper channel and location corresponding to the input pattern scale and its presence. Then, we accomplish the hierarchical scale attention by stacking the reformed layers, building a novel style named SCale AttentioN Conv Neural Network (\textbf{SCAN-CNN}). We apply SCAN-CNN to the face recognition task and push the frontier of SOTA performance. The accuracy gain is more evident when the face images are blurry. Meanwhile, as a single-shot scheme, the inference is more efficient than multi-shot fusion. A set of tools are made to ensure the fast training of SCAN-CNN and zero increase of inference cost compared with the plain CNN.

Kai Zhao, Dongliang Nie, Yuchen Lin et al.

Joint-Embedding Predictive Architectures (JEPAs) provide a simpleframework for learning world models by predicting future latent representations.However, JEPA training is subject to a bias-variance tradeoff.Without sufficient structural constraints, excessive representationalvariance causes the model to collapse to trivial solutions.The recent LeWorldModel (LeWM) shows that this issue can be alleviated bysimply constraining latent embeddings with an isotropic Gaussian prior.However, latent representations inherently lie on low-dimensional manifoldswithin a high-dimensional ambient space, and enforcing an isotropic Gaussianprior directly in this ambient space introduces an overly strong bias.In this work, we propose ame, which seeks a favorable operatingpoint on the bias-variance frontier by applying Gaussian constraints inmultiple random subspaces rather than in the originalembedding space.This design relaxes the global constraint while preserving itsanti-collapse effect, leading to a better balance between trainingstability and representation flexibility.Extensive experiments across fourcontinuous-control environments demonstrate that consistentlyoutperforms LeWM with very clear margins.Our method is simple yet effective, and serves as a strong baseline for future JEPA-based world model research.fdefinedeeemodeThe code is available at https://github.com/intcomp/Sub-JEPA.

Shuaitao Zhao, Kun Liu, Yuhang Huang et al.

Human pose estimation aims to figure out the keypoints of all people in different scenes. Current approaches still face some challenges despite promising results. Existing top-down methods deal with a single person individually, without the interaction between different people and the scene they are situated in. Consequently, the performance of human detection degrades when serious occlusion happens. On the other hand, existing bottom-up methods consider all people at the same time and capture the global knowledge of the entire image. However, they are less accurate than the top-down methods due to the scale variation. To address these problems, we propose a novel Dual-Pipeline Integrated Transformer (DPIT) by integrating top-down and bottom-up pipelines to explore the visual clues of different receptive fields and achieve their complementarity. Specifically, DPIT consists of two branches, the bottom-up branch deals with the whole image to capture the global visual information, while the top-down branch extracts the feature representation of local vision from the single-human bounding box. Then, the extracted feature representations from bottom-up and top-down branches are fed into the transformer encoder to fuse the global and local knowledge interactively. Moreover, we define the keypoint queries to explore both full-scene and single-human posture visual clues to realize the mutual complementarity of the two pipelines. To the best of our knowledge, this is one of the first works to integrate the bottom-up and top-down pipelines with transformers for human pose estimation. Extensive experiments on COCO and MPII datasets demonstrate that our DPIT achieves comparable performance to the state-of-the-art methods.

Jianlin Chen, Gongyang Li, Zhijiang Zhang et al.

Transformer-based methods for RGB-D Salient Object Detection (SOD) have gained significant interest, owing to the transformer's exceptional capacity to capture long-range pixel dependencies. Nevertheless, current RGB-D SOD methods face challenges, such as the quadratic complexity of the attention mechanism and the limited local detail extraction. To overcome these limitations, we propose a novel Superpixel Token Enhancing Network (STENet), which introduces superpixels into cross-modal interaction. STENet follows the two-stream encoder-decoder structure. Its cores are two tailored superpixel-driven cross-modal interaction modules, responsible for global and local feature enhancement. Specifically, we update the superpixel generation method by expanding the neighborhood range of each superpixel, allowing for flexible transformation between pixels and superpixels. With the updated superpixel generation method, we first propose the Superpixel Attention Global Enhancing Module to model the global pixel-to-superpixel relationship rather than the traditional global pixel-to-pixel relationship, which can capture region-level information and reduce computational complexity. We also propose the Superpixel Attention Local Refining Module, which leverages pixel similarity within superpixels to filter out a subset of pixels (i.e., local pixels) and then performs feature enhancement on these local pixels, thereby capturing concerned local details. Furthermore, we fuse the globally and locally enhanced features along with the cross-scale features to achieve comprehensive feature representation. Experiments on seven RGB-D SOD datasets reveal that our STENet achieves competitive performance compared to state-of-the-art methods. The code and results of our method are available at https://github.com/Mark9010/STENet.

Hansong Zhang, Shikun Li, Pengju Wang et al.

Training state-of-the-art (SOTA) deep models often requires extensive data, resulting in substantial training and storage costs. To address these challenges, dataset condensation has been developed to learn a small synthetic set that preserves essential information from the original large-scale dataset. Nowadays, optimization-oriented methods have been the primary method in the field of dataset condensation for achieving SOTA results. However, the bi-level optimization process hinders the practical application of such methods to realistic and larger datasets. To enhance condensation efficiency, previous works proposed Distribution-Matching (DM) as an alternative, which significantly reduces the condensation cost. Nonetheless, current DM-based methods still yield less comparable results to SOTA optimization-oriented methods. In this paper, we argue that existing DM-based methods overlook the higher-order alignment of the distributions, which may lead to sub-optimal matching results. Inspired by this, we present a novel DM-based method named M3D for dataset condensation by Minimizing the Maximum Mean Discrepancy between feature representations of the synthetic and real images. By embedding their distributions in a reproducing kernel Hilbert space, we align all orders of moments of the distributions of real and synthetic images, resulting in a more generalized condensed set. Notably, our method even surpasses the SOTA optimization-oriented method IDC on the high-resolution ImageNet dataset. Extensive analysis is conducted to verify the effectiveness of the proposed method. Source codes are available at https://github.com/Hansong-Zhang/M3D.

Pengju Wang, Bochao Liu, Dan Zeng et al.

In practical scenarios, federated learning frequently necessitates training personalized models for each client using heterogeneous data. This paper proposes a backbone self-distillation approach to facilitate personalized federated learning. In this approach, each client trains its local model and only sends the backbone weights to the server. These weights are then aggregated to create a global backbone, which is returned to each client for updating. However, the client's local backbone lacks personalization because of the common representation. To solve this problem, each client further performs backbone self-distillation by using the global backbone as a teacher and transferring knowledge to update the local backbone. This process involves learning two components: the shared backbone for common representation and the private head for local personalization, which enables effective global knowledge transfer. Extensive experiments and comparisons with 12 state-of-the-art approaches demonstrate the effectiveness of our approach.

Hansong Zhang, Shikun Li, Dan Zeng et al.

As the size of the datasets getting larger, accurately annotating such datasets is becoming more impractical due to the expensiveness on both time and economy. Therefore, crowd-sourcing has been widely adopted to alleviate the cost of collecting labels, which also inevitably introduces label noise and eventually degrades the performance of the model. To learn from crowd-sourcing annotations, modeling the expertise of each annotator is a common but challenging paradigm, because the annotations collected by crowd-sourcing are usually highly-sparse. To alleviate this problem, we propose Coupled Confusion Correction (CCC), where two models are simultaneously trained to correct the confusion matrices learned by each other. Via bi-level optimization, the confusion matrices learned by one model can be corrected by the distilled data from the other. Moreover, we cluster the ``annotator groups'' who share similar expertise so that their confusion matrices could be corrected together. In this way, the expertise of the annotators, especially of those who provide seldom labels, could be better captured. Remarkably, we point out that the annotation sparsity not only means the average number of labels is low, but also there are always some annotators who provide very few labels, which is neglected by previous works when constructing synthetic crowd-sourcing annotations. Based on that, we propose to use Beta distribution to control the generation of the crowd-sourcing labels so that the synthetic annotations could be more consistent with the real-world ones. Extensive experiments are conducted on two types of synthetic datasets and three real-world datasets, the results of which demonstrate that CCC significantly outperforms state-of-the-art approaches. Source codes are available at: https://github.com/Hansong-Zhang/CCC.

Kexin Bao, Yong Li, Dan Zeng et al.

Few-shot class-incremental learning (FSCIL) aims to incrementally learn models from a small amount of novel data, which requires strong representation and adaptation ability of models learned under few-example supervision to avoid catastrophic forgetting on old classes and overfitting to novel classes. This work proposes a generative co-memory regularization approach to facilitate FSCIL. In the approach, the base learning leverages generative domain adaptation finetuning to finetune a pretrained generative encoder on a few examples of base classes by jointly incorporating a masked autoencoder (MAE) decoder for feature reconstruction and a fully-connected classifier for feature classification, which enables the model to efficiently capture general and adaptable representations. Using the finetuned encoder and learned classifier, we construct two class-wise memories: representation memory for storing the mean features for each class, and weight memory for storing the classifier weights. After that, the memory-regularized incremental learning is performed to train the classifier dynamically on the examples of few-shot classes in each incremental session by simultaneously optimizing feature classification and co-memory regularization. The memories are updated in a class-incremental manner and they collaboratively regularize the incremental learning. In this way, the learned models improve recognition accuracy, while mitigating catastrophic forgetting over old classes and overfitting to novel classes. Extensive experiments on popular benchmarks clearly demonstrate that our approach outperforms the state-of-the-arts.

Kexin Baoa, Fanzhao Lin, Zichen Wang et al.

Few-shot class-incremental learning (FSCIL) aims to continually adapt a model on a limited number of new-class examples, facing two well-known challenges: catastrophic forgetting and overfitting to new classes. Existing methods tend to freeze more parts of network components and finetune others with an extra memory during incremental sessions. These methods emphasize preserving prior knowledge to ensure proficiency in recognizing old classes, thereby mitigating catastrophic forgetting. Meanwhile, constraining fewer parameters can help in overcoming overfitting with the assistance of prior knowledge. Following previous methods, we retain more prior knowledge and propose a prior knowledge-infused neural network (PKI) to facilitate FSCIL. PKI consists of a backbone, an ensemble of projectors, a classifier, and an extra memory. In each incremental session, we build a new projector and add it to the ensemble. Subsequently, we finetune the new projector and the classifier jointly with other frozen network components, ensuring the rich prior knowledge is utilized effectively. By cascading projectors, PKI integrates prior knowledge accumulated from previous sessions and learns new knowledge flexibly, which helps to recognize old classes and efficiently learn new classes. Further, to reduce the resource consumption associated with keeping many projectors, we design two variants of the prior knowledge-infused neural network (PKIV-1 and PKIV-2) to trade off a balance between resource consumption and performance by reducing the number of projectors. Extensive experiments on three popular benchmarks demonstrate that our approach outperforms state-of-the-art methods.

You Wu, Xucheng Wang, Xiangyang Yang et al.

Single-stream architectures using Vision Transformer (ViT) backbones show great potential for real-time UAV tracking recently. However, frequent occlusions from obstacles like buildings and trees expose a major drawback: these models often lack strategies to handle occlusions effectively. New methods are needed to enhance the occlusion resilience of single-stream ViT models in aerial tracking. In this work, we propose to learn Occlusion-Robust Representations (ORR) based on ViTs for UAV tracking by enforcing an invariance of the feature representation of a target with respect to random masking operations modeled by a spatial Cox process. Hopefully, this random masking approximately simulates target occlusions, thereby enabling us to learn ViTs that are robust to target occlusion for UAV tracking. This framework is termed ORTrack. Additionally, to facilitate real-time applications, we propose an Adaptive Feature-Based Knowledge Distillation (AFKD) method to create a more compact tracker, which adaptively mimics the behavior of the teacher model ORTrack according to the task's difficulty. This student model, dubbed ORTrack-D, retains much of ORTrack's performance while offering higher efficiency. Extensive experiments on multiple benchmarks validate the effectiveness of our method, demonstrating its state-of-the-art performance. Codes is available at https://github.com/wuyou3474/ORTrack.

Enquan Yang, Peng Xing, Hanyang Sun et al.

Industrial anomaly detection achieves progress thanks to datasets such as MVTec-AD and VisA. However, they suffer from limitations in terms of the number of defect samples, types of defects, and availability of real-world scenes. These constraints inhibit researchers from further exploring the performance of industrial detection with higher accuracy. To this end, we propose a new large-scale anomaly detection dataset called 3CAD, which is derived from real 3C production lines. Specifically, the proposed 3CAD includes eight different types of manufactured parts, totaling 27,039 high-resolution images labeled with pixel-level anomalies. The key features of 3CAD are that it covers anomalous regions of different sizes, multiple anomaly types, and the possibility of multiple anomalous regions and multiple anomaly types per anomaly image. This is the largest and first anomaly detection dataset dedicated to 3C product quality control for community exploration and development. Meanwhile, we introduce a simple yet effective framework for unsupervised anomaly detection: a Coarse-to-Fine detection paradigm with Recovery Guidance (CFRG). To detect small defect anomalies, the proposed CFRG utilizes a coarse-to-fine detection paradigm. Specifically, we utilize a heterogeneous distillation model for coarse localization and then fine localization through a segmentation model. In addition, to better capture normal patterns, we introduce recovery features as guidance. Finally, we report the results of our CFRG framework and popular anomaly detection methods on the 3CAD dataset, demonstrating strong competitiveness and providing a highly challenging benchmark to promote the development of the anomaly detection field. Data and code are available: https://github.com/EnquanYang2022/3CAD.

You Wu, Yongxin Li, Mengyuan Liu et al.

Transformer-based models have improved visual tracking, but most still cannot run in real time on resource-limited devices, especially for unmanned aerial vehicle (UAV) tracking. To achieve a better balance between performance and efficiency, we propose AVTrack, an adaptive computation tracking framework that adaptively activates transformer blocks through an Activation Module (AM), which dynamically optimizes the ViT architecture by selectively engaging relevant components. To address extreme viewpoint variations, we propose to learn view-invariant representations via mutual information (MI) maximization. In addition, we propose AVTrack-MD, an enhanced tracker incorporating a novel MI maximization-based multi-teacher knowledge distillation framework. Leveraging multiple off-the-shelf AVTrack models as teachers, we maximize the MI between their aggregated softened features and the corresponding softened feature of the student model, improving the generalization and performance of the student, especially under noisy conditions. Extensive experiments show that AVTrack-MD achieves performance comparable to AVTrack's performance while reducing model complexity and boosting average tracking speed by over 17\%. Codes is available at: https://github.com/wuyou3474/AVTrack.

You Wu, Xiangyang Yang, Xucheng Wang et al.

Harnessing low-light enhancement and domain adaptation, nighttime UAV tracking has made substantial strides. However, over-reliance on image enhancement, limited high-quality nighttime data, and a lack of integration between daytime and nighttime trackers hinder the development of an end-to-end trainable framework. Additionally, current ViT-based trackers demand heavy computational resources due to their reliance on the self-attention mechanism. In this paper, we propose a novel pure Mamba-based tracking framework (MambaNUT) that employs a state space model with linear complexity as its backbone, incorporating a single-stream architecture that integrates feature learning and template-search coupling within Vision Mamba. We introduce an adaptive curriculum learning (ACL) approach that dynamically adjusts sampling strategies and loss weights, thereby improving the model's ability of generalization. Our ACL is composed of two levels of curriculum schedulers: (1) sampling scheduler that transforms the data distribution from imbalanced to balanced, as well as from easier (daytime) to harder (nighttime) samples; (2) loss scheduler that dynamically assigns weights based on the size of the training set and IoU of individual instances. Exhaustive experiments on multiple nighttime UAV tracking benchmarks demonstrate that the proposed MambaNUT achieves state-of-the-art performance while requiring lower computational costs. The code will be available at https://github.com/wuyou3474/MambaNUT.

Ruowei Wang, Jiaqi Li, Dan Zeng et al.

Generating high-quality meshes with complex structures and realistic surfaces is the primary goal of 3D generative models. Existing methods typically employ sequence data or deformable tetrahedral grids for mesh generation. However, sequence-based methods have difficulty producing complex structures with many faces due to memory limits. The deformable tetrahedral grid-based method MeshDiffusion fails to recover realistic surfaces due to the inherent ambiguity in deformable grids. We propose the GenUDC framework to address these challenges by leveraging the Unsigned Dual Contouring (UDC) as the mesh representation. UDC discretizes a mesh in a regular grid and divides it into the face and vertex parts, recovering both complex structures and fine details. As a result, the one-to-one mapping between UDC and mesh resolves the ambiguity problem. In addition, GenUDC adopts a two-stage, coarse-to-fine generative process for 3D mesh generation. It first generates the face part as a rough shape and then the vertex part to craft a detailed shape. Extensive evaluations demonstrate the superiority of UDC as a mesh representation and the favorable performance of GenUDC in mesh generation. The code and trained models are available at https://github.com/TrepangCat/GenUDC.

Pengzhi Zhong, Jiwei Mo, Dan Zeng et al.

Spiking Neural Networks (SNNs), characterized by their event-driven computation and low power consumption, have shown great potential for energy-efficient visual tracking on unmanned aerial vehicles (UAVs). However, existing efficient SNN-based trackers heavily rely on costly event cameras, limiting their deployment on UAVs. To address this limitation, we propose STATrack, an efficient fully spiking neural network framework for UAV visual tracking using RGB inputs only. To the best of our knowledge, this work is the first to investigate spiking neural networks for UAV visual tracking tasks. To mitigate the weakening of target features by background tokens, we propose adaptively maximizing the mutual information between templates and features. Extensive experiments on four widely used UAV tracking benchmarks demonstrate that STATrack achieves competitive tracking performance while maintaining low energy consumption.

Xiangyang Yang, Dan Zeng, Xucheng Wang et al.

Empowered by transformer-based models, visual tracking has advanced significantly. However, the slow speed of current trackers limits their applicability on devices with constrained computational resources. To address this challenge, we introduce ABTrack, an adaptive computation framework that adaptively bypassing transformer blocks for efficient visual tracking. The rationale behind ABTrack is rooted in the observation that semantic features or relations do not uniformly impact the tracking task across all abstraction levels. Instead, this impact varies based on the characteristics of the target and the scene it occupies. Consequently, disregarding insignificant semantic features or relations at certain abstraction levels may not significantly affect the tracking accuracy. We propose a Bypass Decision Module (BDM) to determine if a transformer block should be bypassed, which adaptively simplifies the architecture of ViTs and thus speeds up the inference process. To counteract the time cost incurred by the BDMs and further enhance the efficiency of ViTs, we introduce a novel ViT pruning method to reduce the dimension of the latent representation of tokens in each transformer block. Extensive experiments on multiple tracking benchmarks validate the effectiveness and generality of the proposed method and show that it achieves state-of-the-art performance. Code is released at: https://github.com/xyyang317/ABTrack.

Weiyi Lv, Yuhang Huang, Ning Zhang et al.

In Multiple Object Tracking, objects often exhibit non-linear motion of acceleration and deceleration, with irregular direction changes. Tacking-by-detection (TBD) trackers with Kalman Filter motion prediction work well in pedestrian-dominant scenarios but fall short in complex situations when multiple objects perform non-linear and diverse motion simultaneously. To tackle the complex non-linear motion, we propose a real-time diffusion-based MOT approach named DiffMOT. Specifically, for the motion predictor component, we propose a novel Decoupled Diffusion-based Motion Predictor (D$^2$MP). It models the entire distribution of various motion presented by the data as a whole. It also predicts an individual object's motion conditioning on an individual's historical motion information. Furthermore, it optimizes the diffusion process with much fewer sampling steps. As a MOT tracker, the DiffMOT is real-time at 22.7FPS, and also outperforms the state-of-the-art on DanceTrack and SportsMOT datasets with $62.3\%$ and $76.2\%$ in HOTA metrics, respectively. To the best of our knowledge, DiffMOT is the first to introduce a diffusion probabilistic model into the MOT to tackle non-linear motion prediction.

Wenli Li, Kai Zhao, Haoran Jiang et al.

Vision-language models (VLMs) have been widely adopted for 3D question answering (3D QA). In typical pipelines, visual tokens extracted from multiple viewpoints are concatenated with language tokens and jointly processed by a large language model (LLM) for inference. However, aggregating multi-view observations inevitably introduces severe token redundancy, leading to an overly large visual token set that significantly hinders inference efficiency under constrained token budgets. Visual token pruning has emerged as a prevalent strategy to address this issue. Nevertheless, most existing pruners are primarily tailored to 2D inputs or rely on indirect geometric cues, which limits their ability to explicitly retain semantically critical objects and maintain sufficient spatial coverage for robust 3D reasoning. In this paper, we propose SeGPruner, a semantic-aware and geometry-guided token reduction framework for efficient 3D QA with multi-view images. Specifically, SeGPruner first preserves semantically salient tokens through an attention-based importance module (Saliency-aware Token Selector), ensuring that object-critical evidence is retained. It then complements these tokens with spatially diverse ones via a geometry-guided selector (Geometry-aware Token Diversifier), which jointly considers semantic relevance and 3D geometric distance. This cooperation between saliency preservation and geometry-guided diversification balances object-level evidence and global scene coverage under aggressive token reduction. Extensive experiments on ScanQA and OpenEQA demonstrate that SeGPruner substantially improves inference efficiency, reducing the visual token budget by 91% and inference latency by 86%, while maintaining competitive performance in 3D reasoning tasks.

Junjie Zhang, Tianci Hu, Xiaoshui Huang et al.

Evaluating the performance of Multi-modal Large Language Models (MLLMs), integrating both point cloud and language, presents significant challenges. The lack of a comprehensive assessment hampers determining whether these models truly represent advancements, thereby impeding further progress in the field. Current evaluations heavily rely on classification and caption tasks, falling short in providing a thorough assessment of MLLMs. A pressing need exists for a more sophisticated evaluation method capable of thoroughly analyzing the spatial understanding and expressive capabilities of these models. To address these issues, we introduce a scalable 3D benchmark, accompanied by a large-scale instruction-tuning dataset known as 3DBench, providing an extensible platform for a comprehensive evaluation of MLLMs. Specifically, we establish the benchmark that spans a wide range of spatial and semantic scales, from object-level to scene-level, addressing both perception and planning tasks. Furthermore, we present a rigorous pipeline for automatically constructing scalable 3D instruction-tuning datasets, covering 10 diverse multi-modal tasks with more than 0.23 million QA pairs generated in total. Thorough experiments evaluating trending MLLMs, comparisons against existing datasets, and variations of training protocols demonstrate the superiority of 3DBench, offering valuable insights into current limitations and potential research directions.

Jiawei Hao, Zhiwei Hao, Jianyuan Guo et al.

Mixture-of-Experts (MoE) based Large Language Models (LLMs) have demonstrated impressive performance and computational efficiency. However, their deployment is often constrained by substantial memory demands, primarily due to the need to load numerous expert modules. While existing expert compression techniques like pruning or merging attempt to mitigate this, they often suffer from irreversible knowledge loss or high training overhead. In this paper, we propose a novel expert compression paradigm termed expert replacing, which replaces redundant experts with parameter-efficient modules and recovers their capabilities with low training costs. We find that even a straightforward baseline of this paradigm yields promising performance. Building on this foundation, we introduce LightMoE, a framework that enhances the paradigm by introducing adaptive expert selection, hierarchical expert construction, and an annealed recovery strategy. Experimental results show that LightMoE matches the performance of LoRA fine-tuning at a 30% compression ratio. Even under a more aggressive 50% compression rate, it outperforms existing methods and achieves average performance improvements of 5.6% across five diverse tasks. These findings demonstrate that LightMoE strikes a superior balance among memory efficiency, training efficiency, and model performance.

Kai Zhao, Wubang Yuan, Zheng Wang et al.

Open-Vocabulary Camouflaged Object Segmentation (OVCOS) seeks to segment and classify camouflaged objects from arbitrary categories, presenting unique challenges due to visual ambiguity and unseen categories.Recent approaches typically adopt a two-stage paradigm: first segmenting objects, then classifying the segmented regions using Vision Language Models (VLMs).However, these methods (1) suffer from a domain gap caused by the mismatch between VLMs' full-image training and cropped-region inference, and (2) depend on generic segmentation models optimized for well-delineated objects, making them less effective for camouflaged objects.Without explicit guidance, generic segmentation models often overlook subtle boundaries, leading to imprecise segmentation.In this paper,we introduce a novel VLM-guided cascaded framework to address these issues in OVCOS.For segmentation, we leverage the Segment Anything Model (SAM), guided by the VLM.Our framework uses VLM-derived features as explicit prompts to SAM, effectively directing attention to camouflaged regions and significantly improving localization accuracy.For classification, we avoid the domain gap introduced by hard cropping.Instead, we treat the segmentation output as a soft spatial prior via the alpha channel, which retains the full image context while providing precise spatial guidance, leading to more accurate and context-aware classification of camouflaged objects.The same VLM is shared across both segmentation and classification to ensure efficiency and semantic consistency.Extensive experiments on both OVCOS and conventional camouflaged object segmentation benchmarks demonstrate the clear superiority of our method, highlighting the effectiveness of leveraging rich VLM semantics for both segmentation and classification of camouflaged objects.

Yuzhou Yang, Yangming Zhou, Qichao Ying et al.

This paper reviews and summarizes the research results on fact-based fake news from the perspectives of tasks and problems, algorithm strategies, and datasets. First, the paper systematically explains the task definition and core problems of fact-based fake news detection. Second, the paper summarizes the existing detection methods based on the algorithm principles. Third, the paper analyzes the classic and newly proposed datasets in the field, and summarizes the experimental results on each dataset. Finally, the paper summarizes the advantages and disadvantages of existing methods, proposes several challenges that methods in this field may face, and looks forward to the next stage of research. It is hoped that this paper will provide reference for subsequent work in the field.

Kexin Bao, Daichi Zhang, Yong Li et al.

Few-shot class-incremental learning (FSCIL) aims to continuously recognize novel classes under limited data, which suffers from the key stability-plasticity dilemma: balancing the retention of old knowledge with the acquisition of new knowledge. To address this issue, we divide the task into two different stages and propose a framework termed Static-Dynamic Collaboration (SDC) to achieve a better trade-off between stability and plasticity. Specifically, our method divides the normal pipeline of FSCIL into Static Retaining Stage (SRS) and Dynamic Learning Stage (DLS), which harnesses old static and incremental dynamic class information, respectively. During SRS, we train an initial model with sufficient data in the base session and preserve the key part as static memory to retain fundamental old knowledge. During DLS, we introduce an extra dynamic projector jointly trained with the previous static memory. By employing both stages, our method achieves improved retention of old knowledge while continuously adapting to new classes. Extensive experiments on three public benchmarks and a real-world application dataset demonstrate that our method achieves state-of-the-art performance against other competitors.

Yu Zhu, Dan Zeng, Shuiwang Li et al.

Recent research in Category-Agnostic Pose Estimation (CAPE) has adopted fixed textual keypoint description as semantic prior for two-stage pose matching frameworks. While this paradigm enhances robustness and flexibility by disentangling the dependency of support images, our critical analysis reveals two inherent limitations of static joint embedding: (1) polysemy-induced cross-category ambiguity during the matching process(e.g., the concept "leg" exhibiting divergent visual manifestations across humans and furniture), and (2) insufficient discriminability for fine-grained intra-category variations (e.g., posture and fur discrepancies between a sleeping white cat and a standing black cat). To overcome these challenges, we propose a new framework that innovatively integrates hierarchical cross-modal interaction with dual-stream feature refinement, enhancing the joint embedding with both class-level and instance-specific cues from textual description and specific images. Experiments on the MP-100 dataset demonstrate that, regardless of the network backbone, CapeNext consistently outperforms state-of-the-art CAPE methods by a large margin.

Weiyi Lv, Ning Zhang, Hanyang Sun et al.

Referring Multi-Object Tracking (RMOT) extends conventional multi-object tracking (MOT) by introducing natural language references for multi-modal fusion tracking. RMOT benchmarks only describe the object's appearance, relative positions, and initial motion states. This so-called static regulation fails to capture dynamic changes of the object motion, including velocity changes and motion direction shifts. This limitation not only causes a temporal discrepancy between static references and dynamic vision modality but also constrains multi-modal tracking performance. To address this limitation, we propose a novel Vision-Motion-Reference aligned RMOT framework, named VMRMOT. It integrates a motion modality extracted from object dynamics to enhance the alignment between vision modality and language references through multi-modal large language models (MLLMs). Specifically, we introduce motion-aware descriptions derived from object dynamic behaviors and, leveraging the powerful temporal-reasoning capabilities of MLLMs, extract motion features as the motion modality. We further design a Vision-Motion-Reference Alignment (VMRA) module to hierarchically align visual queries with motion and reference cues, enhancing their cross-modal consistency. In addition, a Motion-Guided Prediction Head (MGPH) is developed to explore motion modality to enhance the performance of the prediction head. To the best of our knowledge, VMRMOT is the first approach to employ MLLMs in the RMOT task for vision-reference alignment. Extensive experiments on multiple RMOT benchmarks demonstrate that VMRMOT outperforms existing state-of-the-art methods.

Kai Zhao, Wubang Yuan, Alex Lingyu Hung et al.

Vision-Language Models (VLMs) typically process a significantly larger number of visual tokens compared to text tokens due to the inherent redundancy in visual signals. Visual token pruning is a promising direction to reduce the computational cost of VLMs by eliminating redundant visual tokens. The text-visual attention score is a widely adopted criterion for visual token pruning as it reflects the relevance of visual tokens to the text input. However, many sequence models exhibit a recency bias, where tokens appearing later in the sequence exert a disproportionately large influence on the model's output. In VLMs, this bias manifests as inflated attention scores for tokens corresponding to the lower regions of the image, leading to suboptimal pruning that disproportionately retains tokens from the image bottom. In this paper, we present an extremely simple yet effective approach to alleviate the recency bias in visual token pruning. We propose a straightforward reweighting mechanism that adjusts the attention scores of visual tokens according to their spatial positions in the image. Our method, termed Position-reweighted Visual Token Pruning, is a plug-and-play solution that can be seamlessly incorporated into existing visual token pruning frameworks without any changes to the model architecture or extra training. Extensive experiments on LVLMs demonstrate that our method improves the performance of visual token pruning with minimal computational overhead.

Pengzhi Zhong, Xinzhe Wang, Dan Zeng et al.

Brain-inspired Spiking Neural Networks (SNNs) exhibit significant potential for low-power computation, yet their application in visual tasks remains largely confined to image classification, object detection, and event-based tracking. In contrast, real-world vision systems still widely use conventional RGB video streams, where the potential of directly-trained SNNs for complex temporal tasks such as multi-object tracking (MOT) remains underexplored. To address this challenge, we propose SMTrack-the first directly trained deep SNN framework for end-to-end multi-object tracking on standard RGB videos. SMTrack introduces an adaptive and scale-aware Normalized Wasserstein Distance loss (Asa-NWDLoss) to improve detection and localization performance under varying object scales and densities. Specifically, the method computes the average object size within each training batch and dynamically adjusts the normalization factor, thereby enhancing sensitivity to small objects. For the association stage, we incorporate the TrackTrack identity module to maintain robust and consistent object trajectories. Extensive evaluations on BEE24, MOT17, MOT20, and DanceTrack show that SMTrack achieves performance on par with leading ANN-based MOT methods, advancing robust and accurate SNN-based tracking in complex scenarios.

P. Bilha Githinji, Xi Yuan, Zhenglin Chen et al.

Realizing sufficient separability between the distributions of healthy and pathological samples is a critical obstacle for pathology detection convolutional models. Moreover, these models exhibit a bias for contrast-based images, with diminished performance on texture-based medical images. This study introduces the notion of a population-level context for pathology detection and employs a graph theoretic approach to model and incorporate it into the latent code of an autoencoder via a refinement module we term PopuSense. PopuSense seeks to capture additional intra-group variations inherent in biomedical data that a local or global context of the convolutional model might miss or smooth out. Proof-of-concept experiments on contrast-based and texture-based images, with minimal adaptation, encounter the existing preference for intensity-based input. Nevertheless, PopuSense demonstrates improved separability in contrast-based images, presenting an additional avenue for refining representations learned by a model.

Jiansheng Fang, Huazhu Fu, Dan Zeng et al.

When encountering a dubious diagnostic case, medical instance retrieval can help radiologists make evidence-based diagnoses by finding images containing instances similar to a query case from a large image database. The similarity between the query case and retrieved similar cases is determined by visual features extracted from pathologically abnormal regions. However, the manifestation of these regions often lacks specificity, i.e., different diseases can have the same manifestation, and different manifestations may occur at different stages of the same disease. To combat the manifestation ambiguity in medical instance retrieval, we propose a novel deep framework called Y-Net, encoding images into compact hash-codes generated from convolutional features by feature aggregation. Y-Net can learn highly discriminative convolutional features by unifying the pixel-wise segmentation loss and classification loss. The segmentation loss allows exploring subtle spatial differences for good spatial-discriminability while the classification loss utilizes class-aware semantic information for good semantic-separability. As a result, Y-Net can enhance the visual features in pathologically abnormal regions and suppress the disturbing of the background during model training, which could effectively embed discriminative features into the hash-codes in the retrieval stage. Extensive experiments on two medical image datasets demonstrate that Y-Net can alleviate the ambiguity of pathologically abnormal regions and its retrieval performance outperforms the state-of-the-art method by an average of 9.27\% on the returned list of 10.

Hailin Shi, Dan Zeng, Yichun Tai et al.

With the recent development of deep convolutional neural networks and large-scale datasets, deep face recognition has made remarkable progress and been widely used in various applications. However, unlike the existing public face datasets, in many real-world scenarios of face recognition, the depth of training dataset is shallow, which means only two face images are available for each ID. With the non-uniform increase of samples, such issue is converted to a more general case, a.k.a long-tail face learning, which suffers from data imbalance and intra-class diversity dearth simultaneously. These adverse conditions damage the training and result in the decline of model performance. Based on the Semi-Siamese Training (SST), we introduce an advanced solution, named Multi-Agent Semi-Siamese Training (MASST), to address these problems. MASST includes a probe network and multiple gallery agents, the former aims to encode the probe features, and the latter constitutes a stack of networks that encode the prototypes (gallery features). For each training iteration, the gallery network, which is sequentially rotated from the stack, and the probe network form a pair of semi-siamese networks. We give the theoretical and empirical analysis that, given the long-tail (or shallow) data and training loss, MASST smooths the loss landscape and satisfies the Lipschitz continuity with the help of multiple agents and the updating gallery queue. The proposed method is out of extra-dependency, thus can be easily integrated with the existing loss functions and network architectures. It is worth noting that, although multiple gallery agents are employed for training, only the probe network is needed for inference, without increasing the inference cost. Extensive experiments and comparisons demonstrate the advantages of MASST for long-tail and shallow face learning.

Hang Du, Hailin Shi, Yinglu Liu et al.

Near-infrared to visible (NIR-VIS) face recognition is the most common case in heterogeneous face recognition, which aims to match a pair of face images captured from two different modalities. Existing deep learning based methods have made remarkable progress in NIR-VIS face recognition, while it encounters certain newly-emerged difficulties during the pandemic of COVID-19, since people are supposed to wear facial masks to cut off the spread of the virus. We define this task as NIR-VIS masked face recognition, and find it problematic with the masked face in the NIR probe image. First, the lack of masked face data is a challenging issue for the network training. Second, most of the facial parts (cheeks, mouth, nose etc.) are fully occluded by the mask, which leads to a large amount of loss of information. Third, the domain gap still exists in the remaining facial parts. In such scenario, the existing methods suffer from significant performance degradation caused by the above issues. In this paper, we aim to address the challenge of NIR-VIS masked face recognition from the perspectives of training data and training method. Specifically, we propose a novel heterogeneous training method to maximize the mutual information shared by the face representation of two domains with the help of semi-siamese networks. In addition, a 3D face reconstruction based approach is employed to synthesize masked face from the existing NIR image. Resorting to these practices, our solution provides the domain-invariant face representation which is also robust to the mask occlusion. Extensive experiments on three NIR-VIS face datasets demonstrate the effectiveness and cross-dataset-generalization capacity of our method.

Kangkai Zhang, Chunhui Zhang, Shikun Li et al.

Knowledge distillation provides an effective way to transfer knowledge via teacher-student learning, where most existing distillation approaches apply a fixed pre-trained model as teacher to supervise the learning of student network. This manner usually brings in a big capability gap between teacher and student networks during learning. Recent researches have observed that a small teacher-student capability gap can facilitate knowledge transfer. Inspired by that, we propose an evolutionary knowledge distillation approach to improve the transfer effectiveness of teacher knowledge. Instead of a fixed pre-trained teacher, an evolutionary teacher is learned online and consistently transfers intermediate knowledge to supervise student network learning on-the-fly. To enhance intermediate knowledge representation and mimicking, several simple guided modules are introduced between corresponding teacher-student blocks. In this way, the student can simultaneously obtain rich internal knowledge and capture its growth process, leading to effective student network learning. Extensive experiments clearly demonstrate the effectiveness of our approach as well as good adaptability in the low-resolution and few-sample visual recognition scenarios.

Hang Du, Hailin Shi, Dan Zeng et al.

Face recognition is one of the most popular and long-standing topics in computer vision. With the recent development of deep learning techniques and large-scale datasets, deep face recognition has made remarkable progress and been widely used in many real-world applications. Given a natural image or video frame as input, an end-to-end deep face recognition system outputs the face feature for recognition. To achieve this, a typical end-to-end system is built with three key elements: face detection, face alignment, and face representation. The face detection locates faces in the image or frame. Then, the face alignment is proceeded to calibrate the faces to the canonical view and crop them with a normalized pixel size. Finally, in the stage of face representation, the discriminative features are extracted from the aligned face for recognition. Nowadays, all of the three elements are fulfilled by the technique of deep convolutional neural network. In this survey article, we present a comprehensive review about the recent advance of each element. To start with, we present an overview of the end-to-end deep face recognition. Then, we review the advance of each element, respectively, covering many aspects such as the to-date algorithm designs, evaluation metrics, datasets, performance comparison, existing challenges, and promising directions for future research. Also, we provide a detailed discussion about the effect of each element on its subsequent elements and the holistic system. Through this survey, we wish to bring contributions in two aspects: first, readers can conveniently identify the methods which are quite strong-baseline style in the subcategory for further exploration; second, one can also employ suitable methods for establishing a state-of-the-art end-to-end face recognition system from scratch.

Dan Zeng, Hailin Shi, Hang Du et al.

The training scheme of deep face recognition has greatly evolved in the past years, yet it encounters new challenges in the large-scale data situation where massive and diverse hard cases occur. Especially in the range of low false accept rate (FAR), there are various hard cases in both positives (intra-class) and negatives (inter-class). In this paper, we study how to make better use of these hard samples for improving the training. The literature approaches this by margin-based formulation in either positive logit or negative logits. However, the correlation between hard positive and hard negative is overlooked, and so is the relation between the margins in positive and negative logits. We find such correlation is significant, especially in the large-scale dataset, and one can take advantage from it to boost the training via relating the positive and negative margins for each training sample. To this end, we propose an explicit collaboration between positive and negative margins sample-wisely. Given a batch of hard samples, a novel Negative-Positive Collaboration loss, named NPCFace, is formulated, which emphasizes the training on both negative and positive hard cases via the collaborative-margin mechanism in the softmax logits, and also brings better interpretation of negative-positive hardness correlation. Besides, the emphasis is implemented with an improved formulation to achieve stable convergence and flexible parameter setting. We validate the effectiveness of our approach on various benchmarks of large-scale face recognition, and obtain advantageous results especially in the low FAR range.

Hang Du, Hailin Shi, Yuchi Liu et al.

Most existing public face datasets, such as MS-Celeb-1M and VGGFace2, provide abundant information in both breadth (large number of IDs) and depth (sufficient number of samples) for training. However, in many real-world scenarios of face recognition, the training dataset is limited in depth, i.e. only two face images are available for each ID. $\textit{We define this situation as Shallow Face Learning, and find it problematic with existing training methods.}$ Unlike deep face data, the shallow face data lacks intra-class diversity. As such, it can lead to collapse of feature dimension and consequently the learned network can easily suffer from degeneration and over-fitting in the collapsed dimension. In this paper, we aim to address the problem by introducing a novel training method named Semi-Siamese Training (SST). A pair of Semi-Siamese networks constitute the forward propagation structure, and the training loss is computed with an updating gallery queue, conducting effective optimization on shallow training data. Our method is developed without extra-dependency, thus can be flexibly integrated with the existing loss functions and network architectures. Extensive experiments on various benchmarks of face recognition show the proposed method significantly improves the training, not only in shallow face learning, but also for conventional deep face data.

Dan Zeng, Raymond Veldhuis, Luuk Spreeuwers

The limited capacity to recognize faces under occlusions is a long-standing problem that presents a unique challenge for face recognition systems and even for humans. The problem regarding occlusion is less covered by research when compared to other challenges such as pose variation, different expressions, etc. Nevertheless, occluded face recognition is imperative to exploit the full potential of face recognition for real-world applications. In this paper, we restrict the scope to occluded face recognition. First, we explore what the occlusion problem is and what inherent difficulties can arise. As a part of this review, we introduce face detection under occlusion, a preliminary step in face recognition. Second, we present how existing face recognition methods cope with the occlusion problem and classify them into three categories, which are 1) occlusion robust feature extraction approaches, 2) occlusion aware face recognition approaches, and 3) occlusion recovery based face recognition approaches. Furthermore, we analyze the motivations, innovations, pros and cons, and the performance of representative approaches for comparison. Finally, future challenges and method trends of occluded face recognition are thoroughly discussed.