Jun Wan

Benjia Zhou, Pichao Wang, Jun Wan et al.

Motion recognition is a promising direction in computer vision, but the training of video classification models is much harder than images due to insufficient data and considerable parameters. To get around this, some works strive to explore multimodal cues from RGB-D data. Although improving motion recognition to some extent, these methods still face sub-optimal situations in the following aspects: (i) Data augmentation, i.e., the scale of the RGB-D datasets is still limited, and few efforts have been made to explore novel data augmentation strategies for videos; (ii) Optimization mechanism, i.e., the tightly space-time-entangled network structure brings more challenges to spatiotemporal information modeling; And (iii) cross-modal knowledge fusion, i.e., the high similarity between multimodal representations caused to insufficient late fusion. To alleviate these drawbacks, we propose to improve RGB-D-based motion recognition both from data and algorithm perspectives in this paper. In more detail, firstly, we introduce a novel video data augmentation method dubbed ShuffleMix, which acts as a supplement to MixUp, to provide additional temporal regularization for motion recognition. Secondly, a Unified Multimodal De-coupling and multi-stage Re-coupling framework, termed UMDR, is proposed for video representation learning. Finally, a novel cross-modal Complement Feature Catcher (CFCer) is explored to mine potential commonalities features in multimodal information as the auxiliary fusion stream, to improve the late fusion results. The seamless combination of these novel designs forms a robust spatiotemporal representation and achieves better performance than state-of-the-art methods on four public motion datasets. Specifically, UMDR achieves unprecedented improvements of +4.5% on the Chalearn IsoGD dataset. Our code is available at https://github.com/zhoubenjia/MotionRGBD-PAMI.

Hao Fang, Ajian Liu, Jun Wan et al.

Face Anti-spoofing (FAS) is essential to secure face recognition systems from various physical attacks. However, recent research generally focuses on short-distance applications (i.e., phone unlocking) while lacking consideration of long-distance scenes (i.e., surveillance security checks). In order to promote relevant research and fill this gap in the community, we collect a large-scale Surveillance High-Fidelity Mask (SuHiFiMask) dataset captured under 40 surveillance scenes, which has 101 subjects from different age groups with 232 3D attacks (high-fidelity masks), 200 2D attacks (posters, portraits, and screens), and 2 adversarial attacks. In this scene, low image resolution and noise interference are new challenges faced in surveillance FAS. Together with the SuHiFiMask dataset, we propose a Contrastive Quality-Invariance Learning (CQIL) network to alleviate the performance degradation caused by image quality from three aspects: (1) An Image Quality Variable module (IQV) is introduced to recover image information associated with discrimination by combining the super-resolution network. (2) Using generated sample pairs to simulate quality variance distributions to help contrastive learning strategies obtain robust feature representation under quality variation. (3) A Separate Quality Network (SQN) is designed to learn discriminative features independent of image quality. Finally, a large number of experiments verify the quality of the SuHiFiMask dataset and the superiority of the proposed CQIL.

Jun Li, Zichang Tan, Jun Wan et al.

The networks trained on the long-tailed dataset vary remarkably, despite the same training settings, which shows the great uncertainty in long-tailed learning. To alleviate the uncertainty, we propose a Nested Collaborative Learning (NCL), which tackles the problem by collaboratively learning multiple experts together. NCL consists of two core components, namely Nested Individual Learning (NIL) and Nested Balanced Online Distillation (NBOD), which focus on the individual supervised learning for each single expert and the knowledge transferring among multiple experts, respectively. To learn representations more thoroughly, both NIL and NBOD are formulated in a nested way, in which the learning is conducted on not just all categories from a full perspective but some hard categories from a partial perspective. Regarding the learning in the partial perspective, we specifically select the negative categories with high predicted scores as the hard categories by using a proposed Hard Category Mining (HCM). In the NCL, the learning from two perspectives is nested, highly related and complementary, and helps the network to capture not only global and robust features but also meticulous distinguishing ability. Moreover, self-supervision is further utilized for feature enhancement. Extensive experiments manifest the superiority of our method with outperforming the state-of-the-art whether by using a single model or an ensemble.

Dong Wang, Jia Guo, Qiqi Shao et al.

Face anti-spoofing (FAS) is an essential mechanism for safeguarding the integrity of automated face recognition systems. Despite substantial advancements, the generalization of existing approaches to real-world applications remains challenging. This limitation can be attributed to the scarcity and lack of diversity in publicly available FAS datasets, which often leads to overfitting during training or saturation during testing. In terms of quantity, the number of spoof subjects is a critical determinant. Most datasets comprise fewer than 2,000 subjects. With regard to diversity, the majority of datasets consist of spoof samples collected in controlled environments using repetitive, mechanical processes. This data collection methodology results in homogenized samples and a dearth of scenario diversity. To address these shortcomings, we introduce the Wild Face Anti-Spoofing (WFAS) dataset, a large-scale, diverse FAS dataset collected in unconstrained settings. Our dataset encompasses 853,729 images of 321,751 spoof subjects and 529,571 images of 148,169 live subjects, representing a substantial increase in quantity. Moreover, our dataset incorporates spoof data obtained from the internet, spanning a wide array of scenarios and various commercial sensors, including 17 presentation attacks (PAs) that encompass both 2D and 3D forms. This novel data collection strategy markedly enhances FAS data diversity. Leveraging the WFAS dataset and Protocol 1 (Known-Type), we host the Wild Face Anti-Spoofing Challenge at the CVPR2023 workshop. Additionally, we meticulously evaluate representative methods using Protocol 1 and Protocol 2 (Unknown-Type). Through an in-depth examination of the challenge outcomes and benchmark baselines, we provide insightful analyses and propose potential avenues for future research. The dataset is released under Insightface.

Hao Fang, Ajian Liu, Jun Wan et al.

Face Anti-spoofing (FAS) is essential to secure face recognition systems from various physical attacks. However, most of the studies lacked consideration of long-distance scenarios. Specifically, compared with FAS in traditional scenes such as phone unlocking, face payment, and self-service security inspection, FAS in long-distance such as station squares, parks, and self-service supermarkets are equally important, but it has not been sufficiently explored yet. In order to fill this gap in the FAS community, we collect a large-scale Surveillance High-Fidelity Mask (SuHiFiMask). SuHiFiMask contains $10,195$ videos from $101$ subjects of different age groups, which are collected by $7$ mainstream surveillance cameras. Based on this dataset and protocol-$3$ for evaluating the robustness of the algorithm under quality changes, we organized a face presentation attack detection challenge in surveillance scenarios. It attracted 180 teams for the development phase with a total of 37 teams qualifying for the final round. The organization team re-verified and re-ran the submitted code and used the results as the final ranking. In this paper, we present an overview of the challenge, including an introduction to the dataset used, the definition of the protocol, the evaluation metrics, and the announcement of the competition results. Finally, we present the top-ranked algorithms and the research ideas provided by the competition for attack detection in long-range surveillance scenarios.

Jun Wan, Jun Liu, Jie Zhou et al.

Most facial landmark detection methods predict landmarks by mapping the input facial appearance features to landmark heatmaps and have achieved promising results. However, when the face image is suffering from large poses, heavy occlusions and complicated illuminations, they cannot learn discriminative feature representations and effective facial shape constraints, nor can they accurately predict the value of each element in the landmark heatmap, limiting their detection accuracy. To address this problem, we propose a novel Reference Heatmap Transformer (RHT) by introducing reference heatmap information for more precise facial landmark detection. The proposed RHT consists of a Soft Transformation Module (STM) and a Hard Transformation Module (HTM), which can cooperate with each other to encourage the accurate transformation of the reference heatmap information and facial shape constraints. Then, a Multi-Scale Feature Fusion Module (MSFFM) is proposed to fuse the transformed heatmap features and the semantic features learned from the original face images to enhance feature representations for producing more accurate target heatmaps. To the best of our knowledge, this is the first study to explore how to enhance facial landmark detection by transforming the reference heatmap information. The experimental results from challenging benchmark datasets demonstrate that our proposed method outperforms the state-of-the-art methods in the literature.

Hanshen Xiao, Jun Wan, Srinivas Devadas

Training large neural networks with meaningful/usable differential privacy security guarantees is a demanding challenge. In this paper, we tackle this problem by revisiting the two key operations in Differentially Private Stochastic Gradient Descent (DP-SGD): 1) iterative perturbation and 2) gradient clipping. We propose a generic optimization framework, called {\em ModelMix}, which performs random aggregation of intermediate model states. It strengthens the composite privacy analysis utilizing the entropy of the training trajectory and improves the $(ε, δ)$ DP security parameters by an order of magnitude. We provide rigorous analyses for both the utility guarantees and privacy amplification of ModelMix. In particular, we present a formal study on the effect of gradient clipping in DP-SGD, which provides theoretical instruction on how hyper-parameters should be selected. We also introduce a refined gradient clipping method, which can further sharpen the privacy loss in private learning when combined with ModelMix. Thorough experiments with significant privacy/utility improvement are presented to support our theory. We train a Resnet-20 network on CIFAR10 with $70.4\%$ accuracy via ModelMix given $(ε=8, δ=10^{-5})$ DP-budget, compared to the same performance but with $(ε=145.8,δ=10^{-5})$ using regular DP-SGD; assisted with additional public low-dimensional gradient embedding, one can further improve the accuracy to $79.1\%$ with $(ε=6.1, δ=10^{-5})$ DP-budget, compared to the same performance but with $(ε=111.2, δ=10^{-5})$ without ModelMix.

Benjia Zhou, Pichao Wang, Jun Wan et al.

Vision Transformers (ViTs) have shown promising performance compared with Convolutional Neural Networks (CNNs), but the training of ViTs is much harder than CNNs. In this paper, we define several metrics, including Dynamic Data Proportion (DDP) and Knowledge Assimilation Rate (KAR), to investigate the training process, and divide it into three periods accordingly: formation, growth and exploration. In particular, at the last stage of training, we observe that only a tiny portion of training examples is used to optimize the model. Given the data-hungry nature of ViTs, we thus ask a simple but important question: is it possible to provide abundant ``effective'' training examples at EVERY stage of training? To address this issue, we need to address two critical questions, \ie, how to measure the ``effectiveness'' of individual training examples, and how to systematically generate enough number of ``effective'' examples when they are running out. To answer the first question, we find that the ``difficulty'' of training samples can be adopted as an indicator to measure the ``effectiveness'' of training samples. To cope with the second question, we propose to dynamically adjust the ``difficulty'' distribution of the training data in these evolution stages. To achieve these two purposes, we propose a novel data-centric ViT training framework to dynamically measure the ``difficulty'' of training samples and generate ``effective'' samples for models at different training stages. Furthermore, to further enlarge the number of ``effective'' samples and alleviate the overfitting problem in the late training stage of ViTs, we propose a patch-level erasing strategy dubbed PatchErasing. Extensive experiments demonstrate the effectiveness of the proposed data-centric ViT training framework and techniques.

Hao Tan, Zichang Tan, Jun Li et al.

Multi-label image recognition is a fundamental task in computer vision. Recently, Vision-Language Models (VLMs) have made notable advancements in this area. However, previous methods fail to effectively leverage the rich knowledge in language models and often incorporate label semantics into visual features unidirectionally. To overcome these problems, we propose a Split-and-Synthesize Prompting with Gated Alignments (SSPA) framework to amplify the potential of VLMs. Specifically, we develop an in-context learning approach to associate the inherent knowledge from LLMs. Then we propose a novel Split-and-Synthesize Prompting (SSP) strategy to first model the generic knowledge and downstream label semantics individually and then aggregate them carefully through the quaternion network. Moreover, we present Gated Dual-Modal Alignments (GDMA) to bidirectionally interact visual and linguistic modalities while eliminating redundant cross-modal information, enabling more efficient region-level alignments. Rather than making the final prediction by a sharp manner in previous works, we propose a soft aggregator to jointly consider results from all image regions. With the help of flexible prompting and gated alignments, SSPA is generalizable to specific domains. Extensive experiments on nine datasets from three domains (i.e., natural, pedestrian attributes and remote sensing) demonstrate the state-of-the-art performance of SSPA. Further analyses verify the effectiveness of SSP and the interpretability of GDMA. The code will be made public.

Zhigang Chen, Benjia Zhou, Yiqing Huang et al.

Sign Language Representation Learning (SLRL) is crucial for a range of sign language-related downstream tasks such as Sign Language Translation (SLT) and Sign Language Retrieval (SLRet). Recently, many gloss-based and gloss-free SLRL methods have been proposed, showing promising performance. Among them, the gloss-free approach shows promise for strong scalability without relying on gloss annotations. However, it currently faces suboptimal solutions due to challenges in encoding the intricate, context-sensitive characteristics of sign language videos, mainly struggling to discern essential sign features using a non-monotonic video-text alignment strategy. Therefore, we introduce an innovative pretraining paradigm for gloss-free SLRL, called C${^2}$RL, in this paper. Specifically, rather than merely incorporating a non-monotonic semantic alignment of video and text to learn language-oriented sign features, we emphasize two pivotal aspects of SLRL: Implicit Content Learning (ICL) and Explicit Context Learning (ECL). ICL delves into the content of communication, capturing the nuances, emphasis, timing, and rhythm of the signs. In contrast, ECL focuses on understanding the contextual meaning of signs and converting them into equivalent sentences. Despite its simplicity, extensive experiments confirm that the joint optimization of ICL and ECL results in robust sign language representation and significant performance gains in gloss-free SLT and SLRet tasks. Notably, C${^2}$RL improves the BLEU-4 score by +5.3 on P14T, +10.6 on CSL-daily, +6.2 on OpenASL, and +1.3 on How2Sign. It also boosts the R@1 score by +8.3 on P14T, +14.4 on CSL-daily, and +5.9 on How2Sign. Additionally, we set a new baseline for the OpenASL dataset in the SLRet task.

Hao Tan, Jun Li, Yizhuang Zhou et al.

Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable generalization capabilities to downstream tasks. However, existing prompt tuning based frameworks need to parallelize learnable textual inputs for all categories, suffering from massive GPU memory consumption when there is a large number of categories in the target dataset. Moreover, previous works require to include category names within prompts, exhibiting subpar performance when dealing with ambiguous category names. To address these shortcomings, we propose Compound Text-Guided Prompt Tuning (TGP-T) that significantly reduces resource demand while achieving superior performance. We introduce text supervision to the optimization of prompts, which enables two benefits: 1) releasing the model reliance on the pre-defined category names during inference, thereby enabling more flexible prompt generation; 2) reducing the number of inputs to the text encoder, which decreases GPU memory consumption significantly. Specifically, we found that compound text supervisions, i.e., category-wise and content-wise, is highly effective, since they provide inter-class separability and capture intra-class variations, respectively. Moreover, we condition the prompt generation on visual features through a module called Bonder, which facilitates the alignment between prompts and visual features. Extensive experiments on few-shot recognition and domain generalization demonstrate that TGP-T achieves superior performance with consistently lower training costs. It reduces GPU memory usage by 93% and attains a 2.5% performance gain on 16-shot ImageNet. The code is available at https://github.com/EricTan7/TGP-T.

Jun Wan, He Liu, Yujia Wu et al.

At present, deep neural network methods have played a dominant role in face alignment field. However, they generally use predefined network structures to predict landmarks, which tends to learn general features and leads to mediocre performance, e.g., they perform well on neutral samples but struggle with faces exhibiting large poses or occlusions. Moreover, they cannot effectively deal with semantic gaps and ambiguities among features at different scales, which may hinder them from learning efficient features. To address the above issues, in this paper, we propose a Dynamic Semantic-Aggregation Transformer (DSAT) for more discriminative and representative feature (i.e., specialized feature) learning. Specifically, a Dynamic Semantic-Aware (DSA) model is first proposed to partition samples into subsets and activate the specific pathways for them by estimating the semantic correlations of feature channels, making it possible to learn specialized features from each subset. Then, a novel Dynamic Semantic Specialization (DSS) model is designed to mine the homogeneous information from features at different scales for eliminating the semantic gap and ambiguities and enhancing the representation ability. Finally, by integrating the DSA model and DSS model into our proposed DSAT in both dynamic architecture and dynamic parameter manners, more specialized features can be learned for achieving more precise face alignment. It is interesting to show that harder samples can be handled by activating more feature channels. Extensive experiments on popular face alignment datasets demonstrate that our proposed DSAT outperforms state-of-the-art models in the literature.Our code is available at https://github.com/GERMINO-LiuHe/DSAT.

Kunchi Li, Jun Wan, Shan Yu

Rehearsal approaches in class incremental learning (CIL) suffer from decision boundary overfitting to new classes, which is mainly caused by two factors: insufficiency of old classes data for knowledge distillation and imbalanced data learning between the learned and new classes because of the limited storage memory. In this work, we present a simple but effective approach to tackle these two factors. First, we employ a re-sampling strategy and Mixup K}nowledge D}istillation (Re-MKD) to improve the performances of KD, which would greatly alleviate the overfitting problem. Specifically, we combine mixup and re-sampling strategies to synthesize adequate data used in KD training that are more consistent with the latent distribution between the learned and new classes. Second, we propose a novel incremental influence balance (IIB) method for CIL to tackle the classification of imbalanced data by extending the influence balance method into the CIL setting, which re-weights samples by their influences to create a proper decision boundary. With these two improvements, we present the effective decision boundary learning algorithm (EDBL) which improves the performance of KD and deals with the imbalanced data learning simultaneously. Experiments show that the proposed EDBL achieves state-of-the-art performances on several CIL benchmarks.

Shengkai Hu, Jiaqi Ma, Jun Wan et al.

All-in-One Image Restoration (AiOIR) aims to recover high-quality images from diverse degradations within a unified framework. However, existing methods often fail to explicitly model degradation types and struggle to adapt their restoration behavior to complex or mixed degradations. To address these issues, we propose ClusIR, a Cluster-Guided Image Restoration framework that explicitly models degradation semantics through learnable clustering and propagates cluster-aware cues across spatial and frequency domains for adaptive restoration. Specifically, ClusIR comprises two key components: a Probabilistic Cluster-Guided Routing Mechanism (PCGRM) and a Degradation-Aware Frequency Modulation Module (DAFMM). The proposed PCGRM disentangles degradation recognition from expert activation, enabling discriminative degradation perception and stable expert routing. Meanwhile, DAFMM leverages the cluster-guided priors to perform adaptive frequency decomposition and targeted modulation, collaboratively refining structural and textural representations for higher restoration fidelity. The cluster-guided synergy seamlessly bridges semantic cues with frequency-domain modulation, empowering ClusIR to attain remarkable restoration results across a wide range of degradations. Extensive experiments on diverse benchmarks validate that ClusIR reaches competitive performance under several scenarios.

Benjia Zhou, Pichao Wang, Jun Wan et al.

Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors. Although previous RGB-D-based motion recognition methods have achieved promising performance through the tightly coupled multi-modal spatiotemporal representation, they still suffer from (i) optimization difficulty under small data setting due to the tightly spatiotemporal-entangled modeling;(ii) information redundancy as it usually contains lots of marginal information that is weakly relevant to classification; and (iii) low interaction between multi-modal spatiotemporal information caused by insufficient late fusion. To alleviate these drawbacks, we propose to decouple and recouple spatiotemporal representation for RGB-D-based motion recognition. Specifically, we disentangle the task of learning spatiotemporal representation into 3 sub-tasks: (1) Learning high-quality and dimension independent features through a decoupled spatial and temporal modeling network. (2) Recoupling the decoupled representation to establish stronger space-time dependency. (3) Introducing a Cross-modal Adaptive Posterior Fusion (CAPF) mechanism to capture cross-modal spatiotemporal information from RGB-D data. Seamless combination of these novel designs forms a robust spatialtemporal representation and achieves better performance than state-of-the-art methods on four public motion datasets. Our code is available at https://github.com/damo-cv/MotionRGBD.

Jun Wan, Zhihui Lai, Jing Li et al.

Recently, heatmap regression has been widely explored in facial landmark detection and obtained remarkable performance. However, most of the existing heatmap regression-based facial landmark detection methods neglect to explore the high-order feature correlations, which is very important to learn more representative features and enhance shape constraints. Moreover, no explicit global shape constraints have been added to the final predicted landmarks, which leads to a reduction in accuracy. To address these issues, in this paper, we propose a Multi-order Multi-constraint Deep Network (MMDN) for more powerful feature correlations and shape constraints learning. Specifically, an Implicit Multi-order Correlating Geometry-aware (IMCG) model is proposed to introduce the multi-order spatial correlations and multi-order channel correlations for more discriminative representations. Furthermore, an Explicit Probability-based Boundary-adaptive Regression (EPBR) method is developed to enhance the global shape constraints and further search the semantically consistent landmarks in the predicted boundary for robust facial landmark detection. It's interesting to show that the proposed MMDN can generate more accurate boundary-adaptive landmark heatmaps and effectively enhance shape constraints to the predicted landmarks for faces with large pose variations and heavy occlusions. Experimental results on challenging benchmark datasets demonstrate the superiority of our MMDN over state-of-the-art facial landmark detection methods. The code has been publicly available at https://github.com/junwan2014/MMDN-master.

Ajian Liu, Haocheng Yuan, Xiao Guo et al.

PAD and FFD are proposed to protect face data from physical media-based Presentation Attacks and digital editing-based DeepFakes, respectively. However, isolated training of these two models significantly increases vulnerability towards unknown attacks, burdening deployment environments. The lack of a Unified Face Attack Detection model to simultaneously handle attacks in these two categories is mainly attributed to two factors: (1) A benchmark that is sufficient for models to explore is lacking. Existing UAD datasets only contain limited attack types and samples, leading to the model's confined ability to address abundant advanced threats. In light of these, through an explainable hierarchical way, we propose the most extensive and sophisticated collection of forgery techniques available to date, namely UniAttackDataPlus. Our UniAttackData+ encompasses 2,875 identities and their 54 kinds of corresponding falsified samples, in a total of 697,347 videos. (2) The absence of a trustworthy classification criterion. Current methods endeavor to explore an arbitrary criterion within the same semantic space, which fails to exist when encountering diverse attacks. Thus, we present a novel Visual-Language Model-based Hierarchical Prompt Tuning Framework that adaptively explores multiple classification criteria from different semantic spaces. Specifically, we construct a VP-Tree to explore various classification rules hierarchically. Then, by adaptively pruning the prompts, the model can select the most suitable prompts guiding the encoder to extract discriminative features at different levels in a coarse-to-fine manner. Finally, to help the model understand the classification criteria in visual space, we propose a DPI module to project the visual prompts to the text encoder to help obtain a more accurate semantics.

Ajian Liu, Zichang Tan, Zitong Yu et al.

The availability of handy multi-modal (i.e., RGB-D) sensors has brought about a surge of face anti-spoofing research. However, the current multi-modal face presentation attack detection (PAD) has two defects: (1) The framework based on multi-modal fusion requires providing modalities consistent with the training input, which seriously limits the deployment scenario. (2) The performance of ConvNet-based model on high fidelity datasets is increasingly limited. In this work, we present a pure transformer-based framework, dubbed the Flexible Modal Vision Transformer (FM-ViT), for face anti-spoofing to flexibly target any single-modal (i.e., RGB) attack scenarios with the help of available multi-modal data. Specifically, FM-ViT retains a specific branch for each modality to capture different modal information and introduces the Cross-Modal Transformer Block (CMTB), which consists of two cascaded attentions named Multi-headed Mutual-Attention (MMA) and Fusion-Attention (MFA) to guide each modal branch to mine potential features from informative patch tokens, and to learn modality-agnostic liveness features by enriching the modal information of own CLS token, respectively. Experiments demonstrate that the single model trained based on FM-ViT can not only flexibly evaluate different modal samples, but also outperforms existing single-modal frameworks by a large margin, and approaches the multi-modal frameworks introduced with smaller FLOPs and model parameters.

Beihang Song, Jing Li, Shan Xue et al.

Oriented object detection is a crucial task in computer vision. Current top-down oriented detection methods usually directly detect entire objects, and not only neglecting the authentic direction of targets, but also do not fully utilise the key semantic information, which causes a decrease in detection accuracy. In this study, we developed a single-stage rotating object detector via two points with a solar corona heatmap (ROTP) to detect oriented objects. The ROTP predicts parts of the object and then aggregates them to form a whole image. Herein, we meticulously represent an object in a random direction using the vertex, centre point with width, and height. Specifically, we regress two heatmaps that characterise the relative location of each object, which enhances the accuracy of locating objects and avoids deviations caused by angle predictions. To rectify the central misjudgement of the Gaussian heatmap on high-aspect ratio targets, we designed a solar corona heatmap generation method to improve the perception difference between the central and non-central samples. Additionally, we predicted the vertex relative to the direction of the centre point to connect two key points that belong to the same goal. Experiments on the HRSC 2016, UCASAOD, and DOTA datasets show that our ROTP achieves the most advanced performance with a simpler modelling and less manual intervention.

Jun Wan, Hui Xi, Jie Zhou et al.

Current fully-supervised facial landmark detection methods have progressed rapidly and achieved remarkable performance. However, they still suffer when coping with faces under large poses and heavy occlusions for inaccurate facial shape constraints and insufficient labeled training samples. In this paper, we propose a semi-supervised framework, i.e., a Self-Calibrated Pose Attention Network (SCPAN) to achieve more robust and precise facial landmark detection in challenging scenarios. To be specific, a Boundary-Aware Landmark Intensity (BALI) field is proposed to model more effective facial shape constraints by fusing boundary and landmark intensity field information. Moreover, a Self-Calibrated Pose Attention (SCPA) model is designed to provide a self-learned objective function that enforces intermediate supervision without label information by introducing a self-calibrated mechanism and a pose attention mask. We show that by integrating the BALI fields and SCPA model into a novel self-calibrated pose attention network, more facial prior knowledge can be learned and the detection accuracy and robustness of our method for faces with large poses and heavy occlusions have been improved. The experimental results obtained for challenging benchmark datasets demonstrate that our approach outperforms state-of-the-art methods in the literature.

Ajian Liu, Chenxu Zhao, Zitong Yu et al.

Face presentation attack detection (PAD) is essential to secure face recognition systems primarily from high-fidelity mask attacks. Most existing 3D mask PAD benchmarks suffer from several drawbacks: 1) a limited number of mask identities, types of sensors, and a total number of videos; 2) low-fidelity quality of facial masks. Basic deep models and remote photoplethysmography (rPPG) methods achieved acceptable performance on these benchmarks but still far from the needs of practical scenarios. To bridge the gap to real-world applications, we introduce a largescale High-Fidelity Mask dataset, namely CASIA-SURF HiFiMask (briefly HiFiMask). Specifically, a total amount of 54,600 videos are recorded from 75 subjects with 225 realistic masks by 7 new kinds of sensors. Together with the dataset, we propose a novel Contrastive Context-aware Learning framework, namely CCL. CCL is a new training methodology for supervised PAD tasks, which is able to learn by leveraging rich contexts accurately (e.g., subjects, mask material and lighting) among pairs of live faces and high-fidelity mask attacks. Extensive experimental evaluations on HiFiMask and three additional 3D mask datasets demonstrate the effectiveness of our method.

Can Gao, Jie Zhoua, Duoqian Miao et al.

Attribute reduction is one of the most important research topics in the theory of rough sets, and many rough sets-based attribute reduction methods have thus been presented. However, most of them are specifically designed for dealing with either labeled data or unlabeled data, while many real-world applications come in the form of partial supervision. In this paper, we propose a rough sets-based semi-supervised attribute reduction method for partially labeled data. Particularly, with the aid of prior class distribution information about data, we first develop a simple yet effective strategy to produce the proxy labels for unlabeled data. Then the concept of information granularity is integrated into the information-theoretic measure, based on which, a novel granular conditional entropy measure is proposed, and its monotonicity is proved in theory. Furthermore, a fast heuristic algorithm is provided to generate the optimal reduct of partially labeled data, which could accelerate the process of attribute reduction by removing irrelevant examples and excluding redundant attributes simultaneously. Extensive experiments conducted on UCI data sets demonstrate that the proposed semi-supervised attribute reduction method is promising and even compares favourably with the supervised methods on labeled data and unlabeled data with true labels in terms of classification performance.

Xianxu Hou, Xiaokang Zhang, Linlin Shen et al.

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

Jun Wan, Zhihui Lai, Linlin Shen et al.

Recently, convolutional neural networks (CNNs)-based facial landmark detection methods have achieved great success. However, most of existing CNN-based facial landmark detection methods have not attempted to activate multiple correlated facial parts and learn different semantic features from them that they can not accurately model the relationships among the local details and can not fully explore more discriminative and fine semantic features, thus they suffer from partial occlusions and large pose variations. To address these problems, we propose a cross-order cross-semantic deep network (CCDN) to boost the semantic features learning for robust facial landmark detection. Specifically, a cross-order two-squeeze multi-excitation (CTM) module is proposed to introduce the cross-order channel correlations for more discriminative representations learning and multiple attention-specific part activation. Moreover, a novel cross-order cross-semantic (COCS) regularizer is designed to drive the network to learn cross-order cross-semantic features from different activation for facial landmark detection. It is interesting to show that by integrating the CTM module and COCS regularizer, the proposed CCDN can effectively activate and learn more fine and complementary cross-order cross-semantic features to improve the accuracy of facial landmark detection under extremely challenging scenarios. Experimental results on challenging benchmark datasets demonstrate the superiority of our CCDN over state-of-the-art facial landmark detection methods.

Jinheng Xie, Jun Wan, Linlin Shen et al.

Although current face alignment algorithms have obtained pretty good performances at predicting the location of facial landmarks, huge challenges remain for faces with severe occlusion and large pose variations, etc. On the contrary, semantic location of facial boundary is more likely to be reserved and estimated on these scenes. Therefore, we study a two-stage but end-to-end approach for exploring the relationship between the facial boundary and landmarks to get boundary-aware landmark predictions, which consists of two modules: the self-calibrated boundary estimation (SCBE) module and the boundary-aware landmark transform (BALT) module. In the SCBE module, we modify the stem layers and employ intermediate supervision to help generate high-quality facial boundary heatmaps. Boundary-aware features inherited from the SCBE module are integrated into the BALT module in a multi-scale fusion framework to better model the transformation from boundary to landmark heatmap. Experimental results conducted on the challenging benchmark datasets demonstrate that our approach outperforms state-of-the-art methods in the literature.

Shifeng Zhang, Yiliang Xie, Jun Wan et al.

Pedestrian detection has achieved significant progress with the availability of existing benchmark datasets. However, there is a gap in the diversity and density between real world requirements and current pedestrian detection benchmarks: 1) most of existing datasets are taken from a vehicle driving through the regular traffic scenario, usually leading to insufficient diversity; 2) crowd scenarios with highly occluded pedestrians are still under represented, resulting in low density. To narrow this gap and facilitate future pedestrian detection research, we introduce a large and diverse dataset named WiderPerson for dense pedestrian detection in the wild. This dataset involves five types of annotations in a wide range of scenarios, no longer limited to the traffic scenario. There are a total of $13,382$ images with $399,786$ annotations, i.e., $29.87$ annotations per image, which means this dataset contains dense pedestrians with various kinds of occlusions. Hence, pedestrians in the proposed dataset are extremely challenging due to large variations in the scenario and occlusion, which is suitable to evaluate pedestrian detectors in the wild. We introduce an improved Faster R-CNN and the vanilla RetinaNet to serve as baselines for the new pedestrian detection benchmark. Several experiments are conducted on previous datasets including Caltech-USA and CityPersons to analyze the generalization capabilities of the proposed dataset and we achieve state-of-the-art performances on these previous datasets without bells and whistles. Finally, we analyze common failure cases and find the classification ability of pedestrian detector needs to be improved to reduce false alarm and miss detection rates. The proposed dataset is available at http://www.cbsr.ia.ac.cn/users/sfzhang/WiderPerson

Yang Feng, Qingkai Shi, Xinyu Gao et al.

Deep neural networks (DNN) have been deployed in many software systems to assist in various classification tasks. In company with the fantastic effectiveness in classification, DNNs could also exhibit incorrect behaviors and result in accidents and losses. Therefore, testing techniques that can detect incorrect DNN behaviors and improve DNN quality are extremely necessary and critical. However, the testing oracle, which defines the correct output for a given input, is often not available in the automated testing. To obtain the oracle information, the testing tasks of DNN-based systems usually require expensive human efforts to label the testing data, which significantly slows down the process of quality assurance. To mitigate this problem, we propose DeepGini, a test prioritization technique designed based on a statistical perspective of DNN. Such a statistical perspective allows us to reduce the problem of measuring misclassification probability to the problem of measuring set impurity, which allows us to quickly identify possibly-misclassified tests. To evaluate, we conduct an extensive empirical study on popular datasets and prevalent DNN models. The experimental results demonstrate that DeepGini outperforms existing coverage-based techniques in prioritizing tests regarding both effectiveness and efficiency. Meanwhile, we observe that the tests prioritized at the front by DeepGini are more effective in improving the DNN quality in comparison with the coverage-based techniques.

Yunxiao Qin, Chenxu Zhao, Zezheng Wang et al.

Deep learning based computer vision fails to work when labeled images are scarce. Recently, Meta learning algorithm has been confirmed as a promising way to improve the ability of learning from few images for computer vision. However, previous Meta learning approaches expose problems: 1) they ignored the importance of attention mechanism for the Meta learner; 2) they didn't give the Meta learner the ability of well using the past knowledge which can help to express images into high representations, resulting in that the Meta learner has to solve few shot learning task directly from the original high dimensional RGB images. In this paper, we argue that the attention mechanism and the past knowledge are crucial for the Meta learner, and the Meta learner should be trained on high representations of the RGB images instead of directly on the original ones. Based on these arguments, we propose two methods: Attention augmented Meta Learning (AML) and Representation based and Attention augmented Meta Learning(RAML). The method AML aims to improve the Meta learner's attention ability by explicitly embedding an attention model into its network. The method RAML aims to give the Meta learner the ability of leveraging the past learned knowledge to reduce the dimension of the original input data by expressing it into high representations, and help the Meta learner to perform well. Extensive experiments demonstrate the effectiveness of the proposed models, with state-of-the-art few shot learning performances on several few shot learning benchmarks. The source code of our proposed methods will be released soon to facilitate further studies on those aforementioned problem.

Pichao Wang, Wanqing Li, Jun Wan et al.

A novel deep neural network training paradigm that exploits the conjoint information in multiple heterogeneous sources is proposed. Specifically, in a RGB-D based action recognition task, it cooperatively trains a single convolutional neural network (named c-ConvNet) on both RGB visual features and depth features, and deeply aggregates the two kinds of features for action recognition. Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power of the deeply learned features and weakens the undesired modality discrepancy by jointly optimizing a ranking loss and a softmax loss for both homogeneous and heterogeneous modalities. The ranking loss consists of intra-modality and cross-modality triplet losses, and it reduces both the intra-modality and cross-modality feature variations. Furthermore, the correlations between RGB and depth data are embedded in the c-ConvNet, and can be retrieved by either of the modalities and contribute to the recognition in the case even only one of the modalities is available. The proposed method was extensively evaluated on two large RGB-D action recognition datasets, ChaLearn LAP IsoGD and NTU RGB+D datasets, and one small dataset, SYSU 3D HOI, and achieved state-of-the-art results.

Pichao Wang, Wanqing Li, Philip Ogunbona et al.

Human motion recognition is one of the most important branches of human-centered research activities. In recent years, motion recognition based on RGB-D data has attracted much attention. Along with the development in artificial intelligence, deep learning techniques have gained remarkable success in computer vision. In particular, convolutional neural networks (CNN) have achieved great success for image-based tasks, and recurrent neural networks (RNN) are renowned for sequence-based problems. Specifically, deep learning methods based on the CNN and RNN architectures have been adopted for motion recognition using RGB-D data. In this paper, a detailed overview of recent advances in RGB-D-based motion recognition is presented. The reviewed methods are broadly categorized into four groups, depending on the modality adopted for recognition: RGB-based, depth-based, skeleton-based and RGB+D-based. As a survey focused on the application of deep learning to RGB-D-based motion recognition, we explicitly discuss the advantages and limitations of existing techniques. Particularly, we highlighted the methods of encoding spatial-temporal-structural information inherent in video sequence, and discuss potential directions for future research.

Jiali Duan, Shuai Zhou, Jun Wan et al.

Recently, the popularity of depth-sensors such as Kinect has made depth videos easily available while its advantages have not been fully exploited. This paper investigates, for gesture recognition, to explore the spatial and temporal information complementarily embedded in RGB and depth sequences. We propose a convolutional twostream consensus voting network (2SCVN) which explicitly models both the short-term and long-term structure of the RGB sequences. To alleviate distractions from background, a 3d depth-saliency ConvNet stream (3DDSN) is aggregated in parallel to identify subtle motion characteristics. These two components in an unified framework significantly improve the recognition accuracy. On the challenging Chalearn IsoGD benchmark, our proposed method outperforms the first place on the leader-board by a large margin (10.29%) while also achieving the best result on RGBD-HuDaAct dataset (96.74%). Both quantitative experiments and qualitative analysis shows the effectiveness of our proposed framework and codes will be released to facilitate future research.

Hugo Jair Escalante, Isabelle Guyon, Vassilis Athitsos et al.

This paper introduces principal motion components (PMC), a new method for one-shot gesture recognition. In the considered scenario a single training-video is available for each gesture to be recognized, which limits the application of traditional techniques (e.g., HMMs). In PMC, a 2D map of motion energy is obtained per each pair of consecutive frames in a video. Motion maps associated to a video are processed to obtain a PCA model, which is used for recognition under a reconstruction-error approach. The main benefits of the proposed approach are its simplicity, easiness of implementation, competitive performance and efficiency. We report experimental results in one-shot gesture recognition using the ChaLearn Gesture Dataset; a benchmark comprising more than 50,000 gestures, recorded as both RGB and depth video with a Kinect camera. Results obtained with PMC are competitive with alternative methods proposed for the same data set.