Recent advances in zero-shot text-to-speech (TTS), driven by language models, diffusion models and masked generation, have achieved impressive naturalness in speech synthesis. Nevertheless, stability and fidelity remain key challenges, manifesting as mispronunciations, audible noise, and quality degradation. To address these issues, we introduce Vox-Evaluator, a multi-level evaluator designed to guide the correction of erroneous speech segments and preference alignment for TTS systems. It is capable of identifying the temporal boundaries of erroneous segments and providing a holistic quality assessment of the generated speech. Specifically, to refine erroneous segments and enhance the robustness of the zero-shot TTS model, we propose to automatically identify acoustic errors with the evaluator, mask the erroneous segments, and finally regenerate speech conditioning on the correct portions. In addition, the fine-gained information obtained from Vox-Evaluator can guide the preference alignment for TTS model, thereby reducing the bad cases in speech synthesize. Due to the lack of suitable training datasets for the Vox-Evaluator, we also constructed a synthesized text-speech dataset annotated with fine-grained pronunciation errors or audio quality issues. The experimental results demonstrate the effectiveness of the proposed Vox-Evaluator in enhancing the stability and fidelity of TTS systems through the speech correction mechanism and preference optimization.

Backdoor attacks intend to inject hidden backdoor into the deep neural networks (DNNs), such that the predictions of infected models will be maliciously changed if the hidden backdoor is activated by the attacker-specified trigger pattern. Since the infected models behave normally on predicting benign samples, the backdoor attack is stealthy and therefore a serious threat to practical applications of DNNs. Currently, most existing backdoor attacks adopted the setting of static trigger, i.e ., triggers across the training and testing images follow the same appearance and are located in the same area. In this paper, we revisit this attack paradigm by analyzing trigger characteristics. We demonstrate that this attack paradigm is vulnerable when the trigger in testing images is not consistent with the one used for training. As such, those attacks are far less effective in the physical world, where the location and appearance of the trigger contained in digitized test samples may be different from that of the one used for training. Besides, we introduce a plug-in attack enhancement module during training, inspired by the expectation over transformation (EOT), to alleviate such inconsistency vulnerability. Based on this plug-in module, we also reveal that the widely adopted data augmentation may exacerbate the security risks of backdoor attacks, although it can enhance model performance. Moreover, we evaluate our methods on multiple benchmark datasets to verify their effectiveness. We hope that our work could inspire more explorations on the properties of backdoor attacks, to facilitate the design of more robust and secure DNNs.

Text-to-image (T2I) diffusion models enable high-quality image generation conditioned on textual prompts. However, fine-tuning these pre-trained models for personalization raises concerns about unauthorized dataset usage. To address this issue, dataset ownership verification (DOV) has recently been proposed, which embeds watermarks into fine-tuning datasets via backdoor techniques. These watermarks remain dormant on benign samples but produce owner-specified outputs when triggered. Despite its promise, the robustness of DOV against copyright evasion attacks (CEA) remains unexplored. In this paper, we investigate how adversaries can circumvent these mechanisms, enabling models trained on watermarked datasets to bypass ownership verification. We begin by analyzing the limitations of potential attacks achieved by backdoor removal, including TPD and T2IShield. In practice, TPD suffers from inconsistent effectiveness due to randomness, while T2IShield fails when watermarks are embedded as local image patches. To this end, we introduce CEAT2I, the first CEA specifically targeting DOV in T2I diffusion models. CEAT2I consists of three stages: (1) motivated by the observation that T2I models converge faster on watermarked samples with respect to intermediate features rather than training loss, we reliably detect watermarked samples; (2) we iteratively ablate tokens from the prompts of detected samples and monitor feature shifts to identify trigger tokens; and (3) we apply a closed-form concept erasure method to remove the injected watermarks. Extensive experiments demonstrate that CEAT2I effectively evades state-of-the-art DOV mechanisms while preserving model performance. The code is available at https://github.com/csyufei/CEAT2I.

Despite recent advances in image-to-video generation, better controllability and local animation are less explored. Most existing image-to-video methods are not locally aware and tend to move the entire scene. However, human artists may need to control the movement of different objects or regions. Additionally, current I2V methods require users not only to describe the target motion but also to provide redundant detailed descriptions of frame contents.These two issues hinder the practical utilization of current I2V tools. In this paper, we propose a practical framework, named Follow-Your-Click, to achieve image animation with a simple user click (for specifying what to move) and a motion prompt (for specifying how to move). Technically, we propose the first-frame masking strategy, which significantly improves the video generation quality, and a motion-augmented module equipped with a motion prompt dataset to improve the motion prompt following abilities of our model. To further control the motion speed, we propose flow-based motion magnitude control to control the speed of target movement more precisely. Extensive experiments compared with 7 baselines, including both commercial tools and research methods on 8 metrics, suggest the superiority of our approach.

Reference-based remote sensing super-resolution (RefRS-SR) method shows great potential for improving both spatial resolution and coverage area of remote sensing images, by which high-resolution (HR) reference images can supplement fine details for low-resolution (LR) but wide coverage images. However, most RefRS-SR methods treat the reference as a static template and unidirectionally transfer the high-frequency information to the LR input. To address the issue of inefficient and inaccurate guided super-resolving, we propose a new RefRS-SR method with dynamic reference textures exploitation dubbed DTESR. The key referenced restoration (Ref Restoration) module consists of three components: correlation generation, texture enhancement and refinement (TER), and adaptive similarity-based fusion to progressively reconstruct high correlation and delicate textures for the LR input. Specifically, both the LR input and reference features are utilized for precise correlation generation. Next, both features are enhanced and refined with the most suitable reference under the guidance of the correlation map. Moreover, a learnable fusion method is designed to maintain the consistency of adjacent pixels. These operations will be iteratively applied to the three reconstruction scales to promote the exploitation of the Ref features. Through comprehensive quantitative and qualitative evaluations, our experimental results demonstrate that DTESR surpasses the current state-of-the-art RefRS-SR methods.

Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks. However, recent works revealed that the CLIP model can be implanted with a downstream-oriented backdoor. On downstream tasks, one victim model performs well on clean samples but predicts a specific target class whenever a specific trigger is present. For injecting a backdoor, existing attacks depend on a large amount of additional data to maliciously fine-tune the entire pre-trained CLIP model, which makes them inapplicable to data-limited scenarios. In this work, motivated by the recent success of learnable prompts, we address this problem by injecting a backdoor into the CLIP model in the prompt learning stage. Our method named BadCLIP is built on a novel and effective mechanism in backdoor attacks on CLIP, i.e., influencing both the image and text encoders with the trigger. It consists of a learnable trigger applied to images and a trigger-aware context generator, such that the trigger can change text features via trigger-aware prompts, resulting in a powerful and generalizable attack. Extensive experiments conducted on 11 datasets verify that the clean accuracy of BadCLIP is similar to those of advanced prompt learning methods and the attack success rate is higher than 99% in most cases. BadCLIP is also generalizable to unseen classes, and shows a strong generalization capability under cross-dataset and cross-domain settings. The code is available at https://github.com/jiawangbai/BadCLIP.

Large vision-language models (VLMs) such as GPT-4 have achieved exceptional performance across various multi-modal tasks. However, the deployment of VLMs necessitates substantial energy consumption and computational resources. Once attackers maliciously induce high energy consumption and latency time (energy-latency cost) during inference of VLMs, it will exhaust computational resources. In this paper, we explore this attack surface about availability of VLMs and aim to induce high energy-latency cost during inference of VLMs. We find that high energy-latency cost during inference of VLMs can be manipulated by maximizing the length of generated sequences. To this end, we propose verbose images, with the goal of crafting an imperceptible perturbation to induce VLMs to generate long sentences during inference. Concretely, we design three loss objectives. First, a loss is proposed to delay the occurrence of end-of-sequence (EOS) token, where EOS token is a signal for VLMs to stop generating further tokens. Moreover, an uncertainty loss and a token diversity loss are proposed to increase the uncertainty over each generated token and the diversity among all tokens of the whole generated sequence, respectively, which can break output dependency at token-level and sequence-level. Furthermore, a temporal weight adjustment algorithm is proposed, which can effectively balance these losses. Extensive experiments demonstrate that our verbose images can increase the length of generated sequences by 7.87× and 8.56× compared to original images on MS-COCO and ImageNet datasets, which presents potential challenges for various applications.

The video-language (VL) pretraining has achieved remarkable improvement in multiple downstream tasks. However, the current VL pretraining framework is hard to extend to multiple modalities (N modalities, N ≥ 3) beyond vision and language. We thus propose LanguageBind, taking the language as the bind across different modalities because the language modality is well-explored and contains rich semantics. Specifically, we freeze the language encoder acquired by VL pretraining and then train encoders for other modalities with contrastive learning. As a result, all modalities are mapped to a shared feature space, implementing multi-modal semantic alignment. While LanguageBind ensures that we can extend VL modalities to N modalities, we also need a high-quality dataset with alignment data pairs centered on language. We thus propose VIDAL-10M with 10 Million data with Video, Infrared, Depth, Audio and their corresponding Language. In our VIDAL-10M, all videos are from short video platforms with complete semantics rather than truncated segments from long videos, and all the video, depth, infrared, and audio modalities are aligned to their textual descriptions. LanguageBind has achieved superior performance on a wide range of 15 benchmarks covering video, audio, depth, and infrared. Moreover, multiple experiments have provided evidence for the effectiveness of LanguageBind in achieving indirect alignment and complementarity among diverse modalities.

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where the adversary manipulates a small portion of training data such that the victim model predicts normally on the benign samples but classifies the triggered samples as the target class. The backdoor attack is an emerging yet threatening training-phase threat, leading to serious risks in DNN-based applications. In this paper, we revisit the trigger patterns of existing backdoor attacks. We reveal that they are either visible or not sparse and therefore are not stealthy enough. More importantly, it is not feasible to simply combine existing methods to design an effective sparse and invisible backdoor attack. To address this problem, we formulate the trigger generation as a bi-level optimization problem with sparsity and invisibility constraints and propose an effective method to solve it. The proposed method is dubbed sparse and invisible backdoor attack (SIBA). We conduct extensive experiments on benchmark datasets under different settings, which verify the effectiveness of our attack and its resistance to existing backdoor defenses. The codes for reproducing main experiments are available athttps://github.com/YinghuaGao/SIBA.

Action tube detection is a challenging task as it requires not only to locate action instances in each frame, but also link them in time. Existing action tube detection methods often employ multi-stage pipelines with complex designs and time-consuming linking procedure. In this paper, we present a simple end-to-end action tube detection method, termed as Sparse Tube Detector (STDet). Unlike those dense action detectors, our core idea is to use a set of learnable tube queries and directly decode them into action tubes (i.e., a set of tracked boxes with action label) from video content. This sparse detection paradigm shares several advantages. First, the large number of hand-crafted anchor candidates in dense action detectors is greatly reduced to a small number of learnable tubes, which results in a more efficient detection framework. Second, our learnable tube queries directly attend the whole video content, which endows our method with the capacity of capturing long-range information for action detection. Finally, our action detector is an end-to-end tube detection without requiring the linking procedure, which directly and explicitly predicts the action boundary instead of depending on the linking strategy. Extensive experiments shows that our STDet outperforms the previous state-of-the-art methods on two challenging untrimmed video action detection datasets of UCF101-24 and MultiSports. We hope our method will be an simple end-to-end tube detection baseline and can inspire new ideas in this direction.

Backdoor attack intends to embed hidden backdoors into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by attacker-specified triggers. This threat could happen when the training process is not fully controlled, such as training on third-party datasets or adopting third-party models, which poses a new and realistic threat. Although backdoor learning is an emerging and rapidly growing research area, there is still no comprehensive and timely review of it. In this article, we present the first comprehensive survey of this realm. We summarize and categorize existing backdoor attacks and defenses based on their characteristics, and provide a unified framework for analyzing poisoning-based backdoor attacks. Besides, we also analyze the relation between backdoor attacks and relevant fields (i.e., adversarial attacks and data poisoning), and summarize widely adopted benchmark datasets. Finally, we briefly outline certain future research directions relying upon reviewed works. A curated list of backdoor-related resources is also available at https://github.com/THUYimingLi/backdoor-learning-resources.

Deep neural network, despite its remarkable capability of discriminating targeted in-distribution samples, shows poor performance on detecting anomalous out-of-distribution data. To address this defect, state-of-the-art solutions choose to train deep networks on an auxiliary dataset of outliers. Various training criteria for these auxiliary outliers are proposed based on heuristic intuitions. However, we find that these intuitively designed outlier training criteria can hurt in-distribution learning and eventually lead to inferior performance. To this end, we identify three causes of the in-distribution incompatibility: contradictory gradient, false likelihood, and distribution shift. Based on our new understandings, we propose a new out-of-distribution detection method by adapting both the top-design of deep models and the loss function. Our method achieves in-distribution compatibility by pursuing less interference with the probabilistic characteristic of in-distribution features. On several benchmarks, our method not only achieves the state-of-the-art out-of-distribution detection performance but also improves the in-distribution accuracy.

Many attack paradigms against deep neural networks have been well studied, such as the backdoor attack in the training stage and the adversarial attack in the inference stage. In this article, we study a novel attack paradigm, the bit-flip based weight attack, which directly modifies weight bits of the attacked model in the deployment stage. To meet various attack scenarios, we propose a general formulation including terms to achieve effectiveness and stealthiness goals and a constraint on the number of bit-flips. Furthermore, benefitting from this extensible and flexible formulation, we present two cases with different malicious purposes, i.e., single sample attack (SSA) and triggered samples attack (TSA). SSA which aims at misclassifying a specific sample into a target class is a binary optimization with determining the state of the binary bits (0 or 1); TSA which is to misclassify the samples embedded with a specific trigger is a mixed integer programming (MIP) with flipped bits and a learnable trigger. Utilizing the latest technique in integer programming, we equivalently reformulate them as continuous optimization problems, whose approximate solutions can be effectively and efficiently obtained by the alternating direction method of multipliers (ADMM) method. Extensive experiments demonstrate the superiority of our methods.

Face recognition has always been courted in computer vision and is especially amenable to situations with significant variations between frontal and profile faces. Traditional techniques make great strides either by synthesizing frontal faces from sizable datasets or by empirical pose invariant learning. In this paper, we propose a completely integrated embedded end-to-end Lie algebra residual architecture (LARNeXt) to achieve pose robust face recognition. First, we explore how the face rotation in the 3D space affects the deep feature generation process of convolutional neural networks (CNNs), and prove that face rotation in the image space is equivalent to an additive residual component in the feature space of CNNs, which is determined solely by the rotation. Second, on the basis of this theoretical finding, we further design three critical subnets to leverage a soft regression subnet with novel multi-fusion attention feature aggregation for efficient pose estimation, a residual subnet for decoding rotation information from input face images, and a gating subnet to learn rotation magnitude for controlling the strength of the residual component that contributes to the feature learning process. Finally, we conduct a large number of ablation experiments, and our quantitative and visualization results both corroborate the credibility of our theory and corresponding network designs. Our comprehensive experimental evaluations on frontal-profile face datasets, general unconstrained face recognition datasets, and industrial-grade tasks demonstrate that our method consistently outperforms the state-of-the-art ones.

This work studies black-box adversarial attacks against deep neural networks (DNNs), where the attacker can only access the query feedback returned by the attacked DNN model, while other information such as model parameters or the training datasets are unknown. One promising approach to improve attack performance is utilizing the adversarial transferability between some white-box surrogate models and the target model (i.e., the attacked model). However, due to the possible differences on model architectures and training datasets between surrogate and target models, dubbed “surrogate biases”, the contribution of adversarial transferability to improving the attack performance may be weakened. To tackle this issue, we innovatively propose a black-box attack method by developing a novel mechanism of adversarial transferability, which is robust to the surrogate biases. The general idea is transferring partial parameters of the conditional adversarial distribution (CAD) of surrogate models, while learning the untransferred parameters based on queries to the target model, to keep the flexibility to adjust the CAD of the target model on any new benign sample. Extensive experiments on benchmark datasets and attacking against real-world API demonstrate the superior attack performance of the proposed method. The code will be available at https://github.com/Kira0096/CGATTACK.

With the recent advancement of deep convolutional neural networks, significant progress has been made in general face recognition. However, the state-of-the-art general face recognition models do not generalize well to occluded face images, which are exactly the common cases in real-world scenarios. The potential reasons are the absences of large-scale occluded face data for training and specific designs for tackling corrupted features brought by occlusions. This article presents a novel face recognition method that is robust to occlusions based on a single end-to-end deep neural network. Our approach, named FROM (Face Recognition with Occlusion Masks), learns to discover the corrupted features from the deep convolutional neural networks, and clean them by the dynamically learned masks. In addition, we construct massive occluded face images to train FROM effectively and efficiently. FROM is simple yet powerful compared to the existing methods that either rely on external detectors to discover the occlusions or employ shallow models which are less discriminative. Experimental results on the LFW, Megaface challenge 1, RMF2, AR dataset and other simulated occluded/masked datasets confirm that FROM dramatically improves the accuracy under occlusions, and generalizes well on general face recognition.

Generative Adversarial Networks (GANs) are formulated as minimax game problems that generative networks attempt to approach real data distributions by adversarial learning against discriminators which learn to distinguish generated samples from real ones, of which the intrinsic problem complexity poses challenges to performance and robustness. In this work, we aim to boost model learning from the perspective of network architectures, by incorporating recent progress on automated architecture search into GANs. Specially we propose a fully differentiable search framework, dubbedalphaGAN, where the searching process is formalized as solving a bi-level minimax optimization problem. The outer-level objective aims for seeking an optimal network architecture towards pure Nash Equilibrium conditioned on the network parameters of generators and discriminators optimized with a traditional adversarial loss within inner level. The entire optimization performs a first-order approach by alternately minimizing the two-level objective in a fully differentiable manner that enables obtaining a suitable architecture efficiently from an enormous search space. Extensive experiments on CIFAR-10 and STL-10 datasets show that our algorithm can obtain high-performing architectures only with 3-GPU hours on a single GPU in the search space comprised of approximate$2\times 10^{11}$possible configurations. We further validate the method on the state-of-the-art network StyleGAN2, and push the score of Fréchet Inception Distance (FID) further, i.e., achieving 1.94 on CelebA, 2.86 on LSUN-church and 2.75 on FFHQ, with relative improvements$3\%{\sim} 26\%$over the baseline architecture. We also provide a comprehensive analysis of the behavior of the searching process and the properties of searched architectures, which would benefit further research on architectures for generative models. Codes and models are available athttps://github.com/yuesongtian/AlphaGAN.

In real-world scenarios, many factors may harm face recognition performance,e.g., large pose, bad illumination, low resolution, blur and noise. To address these challenges, previous efforts usually first restore the low-quality faces to high-quality ones and then perform face recognition. However, most of these methods are stage-wise, which is sub-optimal and deviates from the reality. In this paper, we address all these challenges jointly for unconstrained face recognition. We propose anMulti-DegradationFaceRestoration (MDFR) model to restore frontalized high-quality faces from the given low-quality ones under arbitrary facial poses, with three distinct novelties. First, MDFR is a well-designed encoder-decoder architecture which extracts feature representation from an input face image with arbitrary low-quality factors and restores it to a high-quality counterpart. Second, MDFR introduces a pose residual learning strategy along with a 3D-basedPoseNormalizationModule (PNM), which can perceive the pose gap between the input initial pose and its real-frontal pose to guide the face frontalization. Finally, MDFR can generate frontalized high-quality face images by a single unified network, showing a strong capability of preserving face identity. Qualitative and quantitative experiments on both controlled and in-the-wild benchmarks demonstrate the superiority of MDFR over state-of-the-art methods on both face frontalization and face restoration.

We present a versatile model, FaceAnime, for various video generation tasks from still images. Video generation from a single face image is an interesting problem and usually tackled by utilizing Generative Adversarial Networks (GANs) to integrate information from the input face image and a sequence of sparse facial landmarks. However, the generated face images usually suffer from quality loss, image distortion, identity change, and expression mismatching due to the weak representation capacity of the facial landmarks. In this paper, we propose to “imagine” a face video from a single face image according to the reconstructed 3D face dynamics, aiming to generate a realistic and identity-preserving face video, with precisely predicted pose and facial expression. The 3D dynamics reveal changes of the facial expression and motion, and can serve as a strong prior knowledge for guiding highly realistic face video generation. In particular, we explore face video prediction and exploit a well-designed 3D dynamic prediction network to predict a 3D dynamic sequence for a single face image. The 3D dynamics are then further rendered by the sparse texture mapping algorithm to recover structural details and sparse textures for generating face frames. Our model is versatile for various AR/VR and entertainment applications, such as face video retargeting and face video prediction. Superior experimental results have well demonstrated its effectiveness in generating high-fidelity, identity-preserving, and visually pleasant face video clips from a single source face image.

Image inpainting has made remarkable progress with recent advances in deep learning. Popular networks mainly follow an encoder-decoder architecture (sometimes with skip connections) and possess sufficiently large receptive field, i.e., larger than the image resolution. The receptive field refers to the set of input pixels that are path-connected to a neuron. For image inpainting task, however, the size of surrounding areas needed to repair different kinds of missing regions are different, and the very large receptive field is not always optimal, especially for the local structures and textures. In addition, a large receptive field tends to involve more undesired completion results, which will disturb the inpainting process. Based on these insights, we rethink the process of image inpainting from a different perspective of receptive field, and propose a novel three-stage inpainting framework with local and global refinement. Specifically, we first utilize an encoder-decoder network with skip connection to achieve coarse initial results. Then, we introduce a shallow deep model with small receptive field to conduct the local refinement, which can also weaken the influence of distant undesired completion results. Finally, we propose an attention-based encoder-decoder network with large receptive field to conduct the global refinement. Experimental results demonstrate that our method outperforms the state of the arts on three popular publicly available datasets for image inpainting. Our local and global refinement network can be directly inserted into the end of any existing networks to further improve their inpainting performance. Code is available at https://github.com/weizequan/LGNet.git.

With the recent success of deep neural networks, remarkable progress has been achieved on face recognition. However, collecting large-scale real-world training data for face recognition has turned out to be challenging, especially due to the label noise and privacy issues. Meanwhile, existing face recognition datasets are usually collected from web images, lacking detailed annotations on attributes (e.g., pose and expression), so the influences of different attributes on face recognition have been poorly investigated. In this paper, we address the above-mentioned issues in face recognition using synthetic face images, i.e., SynFace. Specifically, we first explore the performance gap between recent state-of-the-art face recognition models trained with synthetic and real face images. We then analyze the underlying causes behind the performance gap, e.g., the poor intraclass variations and the domain gap between synthetic and real face images. Inspired by this, we devise the SynFace with identity mixup (IM) and domain mixup (DM) to mitigate the above performance gap, demonstrating the great potentials of synthetic data for face recognition. Furthermore, with the controllable face synthesis model, we can easily manage different factors of synthetic face generation, including pose, expression, illumination, the number of identities, and samples per identity. Therefore, we also perform a systematically empirical analysis on synthetic face images to provide some insights on how to effectively utilize synthetic data for face recognition.

This paper deals with a challenging task of video scene graph generation (VidSGG), which could serve as a structured video representation for high-level understanding tasks. We present a new detect-to-track paradigm for this task by decoupling the context modeling for relation prediction from the complicated low-level entity tracking. Specifically, we design an efficient method for frame-level VidSGG, termed as Target Adaptive Context Aggregation Network (TRACE), with a focus on capturing spatio-temporal context information for relation recognition. Our TRACE framework streamlines the VidSGG pipeline with a modular design, and presents two unique blocks of Hierarchical Relation Tree (HRTree) construction and Target-adaptive Context Aggregation. More specific, our HRTree first provides an adpative structure for organizing possible relation candidates efficiently, and guides context aggregation module to effectively capture spatio-temporal structure information. Then, we obtain a contextualized feature representation for each relation candidate and build a classification head to recognize its relation category. Finally, we provide a simple temporal association strategy to track TRACE detected results to yield the video-level VidSGG. We perform experiments on two VidSGG benchmarks: ImageNet-VidVRD and Action Genome, and the results demonstrate that our TRACE achieves the state-of-the-art performance. The code and models are made available at https://github.com/MCG-NJU/TRACE.

Face recognition is an important yet challenging problem in computer vision. A major challenge in practical face recognition applications lies in significant variations between profile and frontal faces. Traditional techniques address this challenge either by synthesizing frontal faces or by pose invariant learning. In this paper, we propose a novel method with Lie algebra theory to explore how face rotation in the 3D space affects the deep feature generation process of convolutional neural networks (CNNs). We prove that face rotation in the image space is equivalent to an additive residual component in the feature space of CNNs, which is determined solely by the rotation. Based on this theoretical finding, we further design a Lie Algebraic Residual Network (LARNet) for tackling pose robust face recognition. Our LARNet consists of a residual subnet for decoding rotation information from input face images, and a gating subnet to learn rotation magnitude for controlling the strength of the residual component contributing to the feature learning process. Comprehensive experimental evaluations on both frontal-profile face datasets and general face recognition datasets convincingly demonstrate that our method consistently outperforms the state-of-the-art ones.

We present a face photo-sketch synthesis model, which converts a face photo into an artistic face sketch or recover a photo-realistic facial image from a sketch portrait. Recent progress has been made by convolutional neural networks (CNNs) and generative adversarial networks (GANs), so that promising results can be obtained through real-time end-to-end architectures. However, convolutional architectures tend to focus on local information and neglect long-range spatial dependency, which limits the ability of existing approaches in keeping global structural information. In this paper, we propose a Sketch-Transformer network for face photo-sketch synthesis, which consists of three closely-related modules, including a multi-scale feature and position encoder for patch-level feature and position embedding, a self-attention module for capturing long-range spatial dependency, and a multi-scale spatially-adaptive de-normalization decoder for image reconstruction. Such a design enables the model to generate reasonable detail texture while maintaining global structural information. Extensive experiments show that the proposed method achieves significant improvements over state-of-the-art approaches on both quantitative and qualitative evaluations.

Recent Convolutional Neural Networks (CNNs) have achieved significant success by stacking multiple convolutional blocks, named procedures in this paper, to extract semantic features. However, they use the same procedure sequence for all inputs, regardless of the intermediate features.This paper proffers a simple yet effective idea of constructing parallel procedures and assigning similar intermediate features to the same specialized procedures in a divide-and-conquer fashion. It relieves each procedure's learning difficulty and thus leads to superior performance. Specifically, we propose a routing-by-memory mechanism for existing CNN architectures. In each stage of the network, we introduce parallel Procedural Units (PUs). A PU consists of a memory head and a procedure. The memory head maintains a summary of a type of features. For an intermediate feature, we search its closest memory and forward it to the corresponding procedure in both training and testing. In this way, different procedures are tailored to different features and therefore tackle them better.Networks with the proposed mechanism can be trained efficiently using a four-step training strategy. Experimental results show that our method improves VGGNet, ResNet, and EfficientNet's accuracies on Tiny ImageNet, ImageNet, and CIFAR-100 benchmarks with a negligible extra computational cost.

Knowledge distillation has proven to be an effective model compression method that exploits the knowledge from a teacher model for supervising a student model by minimizing the distribution difference between the knowledge and the prediction produced by the student model. In this work, we focus on improving its performance from the perspective of divergence measures. A general form representing a family of divergence measures is introduced and a novel learning paradigm that jointly optimizes multiple measures is proposed by formalizing it as a multi-objective learning problem. Conditioned on Pareto optimality, the weights of different divergences are tuned in an automated way during training. Extensive experiments on multiple datasets show the proposed method can significantly improve the performance of student networks compared to the state-of-the-art methods for knowledge distillation. Codes are available at https://github.com/CML00/MoDiv.

Recent research has witnessed advances in facial image editing tasks including face swapping and face reenactment. However, these methods are confined to dealing with one specific task at a time. In addition, for video facial editing, previous methods either simply apply transformations frame by frame or utilize multiple frames in a concatenated or iterative fashion, which leads to noticeable visual flickers. In this paper, we propose a unified temporally consistent facial video editing framework termed UniFaceGAN. Based on a 3D reconstruction model and a simple yet efficient dynamic training sample selection mechanism, our framework is designed to handle face swapping and face reenactment simultaneously. To enforce the temporal consistency, a novel 3D temporal loss constraint is introduced based on the barycentric coordinate interpolation. Besides, we propose a region-aware conditional normalization layer to replace the traditional AdaIN or SPADE to synthesize more context-harmonious results. Compared with the state-of-the-art facial image editing methods, our framework generates video portraits that are more photo-realistic and temporally smooth.

General image super-resolution techniques have difficulties in recovering detailed face structures when applying to low resolution face images. Recent deep learning based methods tailored for face images have achieved improved performance by jointly trained with additional task such as face parsing and landmark prediction. However, multi-task learning requires extra manually labeled data. Besides, most of the existing works can only generate relatively low resolution face images (e.g., 128×128 ), and their applications are therefore limited. In this paper, we introduce a novel SPatial Attention Residual Network (SPARNet) built on our newly proposed Face Attention Units (FAUs) for face super-resolution. Specifically, we introduce a spatial attention mechanism to the vanilla residual blocks. This enables the convolutional layers to adaptively bootstrap features related to the key face structures and pay less attention to those less feature-rich regions. This makes the training more effective and efficient as the key face structures only account for a very small portion of the face image. Visualization of the attention maps shows that our spatial attention network can capture the key face structures well even for very low resolution faces (e.g., 16×16 ). Quantitative comparisons on various kinds of metrics (including PSNR, SSIM, identity similarity, and landmark detection) demonstrate the superiority of our method over current state-of-the-arts. We further extend SPARNet with multi-scale discriminators, named as SPARNetHD, to produce high resolution results (i.e., 512×512 ). We show that SPARNetHD trained with synthetic data can not only produce high quality and high resolution outputs for synthetically degraded face images, but also show good generalization ability to real world low quality face images. Codes are available at https://github.com/chaofengc/Face-SPARNet.

Weakly Supervised Temporal Action Localization (WTAL) aims to localize action segments in untrimmed videos with only video-level category labels in the training phase. In WTAL, an action generally consists of a series of sub-actions, and different categories of actions may share the common sub-actions. However, to distinguish different categories of actions with only video-level class labels, current WTAL models tend to focus on discriminative sub-actions of the action, while ignoring those common sub-actions shared with different categories of actions. This negligence of common sub-actions would lead to the located action segments incomplete, i.e., only containing discriminative sub-actions. Different from current approaches of designing complex network architectures to explore more complete actions, in this paper, we introduce a novel supervision method named multi-hierarchical category supervision (MHCS) to find more sub-actions rather than only the discriminative ones. Specifically, action categories sharing similar sub-actions will be constructed as super-classes through hierarchical clustering. Hence, training with the new generated super-classes would encourage the model to pay more attention to the common sub-actions, which are ignored training with the original classes. Furthermore, our proposed MHCS is model-agnostic and non-intrusive, which can be directly applied to existing methods without changing their structures. Through extensive experiments, we verify that our supervision method can improve the performance of four state-of-the-art WTAL methods on three public datasets: THUMOS14, ActivityNet1.2, and ActivityNet1.3.

Existing face super-resolution (SR) methods mainly assume the input image to be noise-free. Their performance degrades drastically when applied to real-world scenarios where the input image is always contaminated by noise. In this paper, we propose a Facial Attribute Capsules Network (FACN) to deal with the problem of high-scale super-resolution of noisy face image. Capsule is a group of neurons whose activity vector models different properties of the same entity. Inspired by the concept of capsule, we propose an integrated representation model of facial information, which named Facial Attribute Capsule (FAC). In the SR processing, we first generated a group of FACs from the input LR face, and then reconstructed the HR face from this group of FACs. Aiming to effectively improve the robustness of FAC to noise, we generate FAC in semantic, probabilistic and facial attributes manners by means of integrated learning strategy. Each FAC can be divided into two sub-capsules: Semantic Capsule (SC) and Probabilistic Capsule (PC). Them describe an explicit facial attribute in detail from two aspects of semantic representation and probability distribution. The group of FACs model an image as a combination of facial attribute information in the semantic space and probabilistic space by an attribute-disentangling way. The diverse FACs could better combine the face prior information to generate the face images with fine-grained semantic attributes. Extensive benchmark experiments show that our method achieves superior hallucination results and outperforms state-of-the-art for very low resolution (LR) noise face image super resolution.

Video super-resolution (VSR) methods have recently achieved a remarkable success due to the development of deep convolutional neural networks (CNN). Current state-of-the-art CNN methods usually treat the VSR problem as a large number of separate multi-frame super-resolution tasks, at which a batch of low resolution (LR) frames is utilized to generate a single high resolution (HR) frame, and running a slide window to select LR frames over the entire video would obtain a series of HR frames. However, duo to the complex temporal dependency between frames, with the number of LR input frames increase, the performance of the reconstructed HR frames become worse. The reason is in that these methods lack the ability to model complex temporal dependencies and hard to give an accurate motion estimation and compensation for VSR process. Which makes the performance degrade drastically when the motion in frames is complex. In this paper, we propose a Motion-Adaptive Feedback Cell (MAFC), a simple but effective block, which can efficiently capture the motion compensation and feed it back to the network in an adaptive way. Our approach efficiently utilizes the information of the inter-frame motion, the dependence of the network on motion estimation and compensation method can be avoid. In addition, benefiting from the excellent nature of MAFC, the network can achieve better performance in the case of extremely complex motion scenarios. Extensive evaluations and comparisons validate the strengths of our approach, and the experimental results demonstrated that the proposed framework is outperform the state-of-the-art methods.

Abstract Recent GAN‐based image inpainting approaches adopt an average strategy to discriminate the generated image and output a scalar, which inevitably lose the position information of visual artifacts. Moreover, the adversarial loss and reconstruction loss (e.g., ℓ1loss) are combined with tradeoff weights, which are also difficult to tune. In this paper, we propose a novel detection‐based generative framework for image inpainting, which adopts the min‐max strategy in an adversarial process. The generator follows an encoder‐decoder architecture to fill the missing regions, and the detector using weakly supervised learning localizes the position of artifacts in a pixel‐wise manner. Such position information makes the generator pay attention to artifacts and further enhance them. More importantly, we explicitly insert the output of the detector into the reconstruction loss with a weighting criterion, which balances the weight of the adversarial loss and reconstruction loss automatically rather than manual operation. Experiments on multiple public datasets show the superior performance of the proposed framework. The source code is available at https://github.com/Evergrow/GDN_Inpainting.

There has been an increasing research interest in age-invariant face recognition. However, matching faces with big age gaps remains a challenging problem, primarily due to the significant discrepancy of face appearance caused by aging. To reduce such discrepancy, in this paper we present a novel algorithm to remove age-related components from features mixed with both identity and age information. Specifically, we factorize a mixed face feature into two uncorrelated components: identity-dependent component and age-dependent component, where the identity-dependent component contains information that is useful for face recognition. To implement this idea, we propose the Decorrelated Adversarial Learning (DAL) algorithm, where a Canonical Mapping Module (CMM) is introduced to find maximum correlation of the paired features generated by the backbone network, while the backbone network and the factorization module are trained to generate features reducing the correlation. Thus, the proposed model learns the decomposed features of age and identity whose correlation is significantly reduced. Simultaneously, the identity-dependent feature and the age-dependent feature are supervised by ID and age preserving signals respectively to ensure they contain the correct information. Extensive experiments have been conducted on the popular public-domain face aging datasets (FG-NET, MORPH Album 2, and CACD-VS) to demonstrate the effectiveness of the proposed approach.

Face recognition has obtained remarkable progress in recent years due to the great improvement of deep convolutional neural networks (CNNs). However, deep CNNs are vulnerable to adversarial examples, which can cause fateful consequences in real-world face recognition applications with security-sensitive purposes. Adversarial attacks are widely studied as they can identify the vulnerability of the models before they are deployed. In this paper, we evaluate the robustness of state-of-the-art face recognition models in the decision-based black-box attack setting, where the attackers have no access to the model parameters and gradients, but can only acquire hard-label predictions by sending queries to the target model. This attack setting is more practical in real-world face recognition systems. To improve the efficiency of previous methods, we propose an evolutionary attack algorithm, which can model the local geometry of the search directions and reduce the dimension of the search space. Extensive experiments demonstrate the effectiveness of the proposed method that induces a minimum perturbation to an input face image with fewer queries. We also apply the proposed method to attack a real-world face recognition system successfully.

Recent studies have witnessed the successes of using 3D CNNs for video action recognition. However, most 3D models are built upon RGB and optical flow streams, which may not fully exploit pose dynamics, i.e., an important cue of modeling human actions. To fill this gap, we propose a concise Pose-Action 3D Machine (PA3D), which can effectively encode multiple pose modalities within a unified 3D framework, and consequently learn spatio-temporal pose representations for action recognition. More specifically, we introduce a novel temporal pose convolution to aggregate spatial poses over frames. Unlike the classical temporal convolution, our operation can explicitly learn the pose motions that are discriminative to recognize human actions. Extensive experiments on three popular benchmarks (i.e., JHMDB, HMDB, and Charades) show that, PA3D outperforms the recent pose-based approaches. Furthermore, PA3D is highly complementary to the recent 3D CNNs, e.g., I3D. Multi-stream fusion achieves the state-of-the-art performance on all evaluated data sets.

Face anti-spoofing is an important task in full-stack face applications including face detection, verification, and recognition. Previous approaches build models on datasets which do not simulate the real-world data well (e.g., small scale, insignificant variance, etc.). Existing models may rely on auxiliary information, which prevents these anti-spoofing solutions from generalizing well in practice. In this paper, we present a data collection solution along with a data synthesis technique to simulate digital medium-based face spoofing attacks, which can easily help us obtain a large amount of training data well reflecting the real-world scenarios. Through exploiting a novel Spatio-Temporal Anti-Spoof Network (STASN), we are able to push the performance on public face anti-spoofing datasets over state-of-the-art methods by a large margin. Since the proposed model can automatically attend to discriminative regions, it makes analyzing the behaviors of the network possible.We conduct extensive experiments and show that the proposed model can distinguish spoof faces by extracting features from a variety of regions to seek out subtle evidences such as borders, moire patterns, reflection artifacts, etc.

Facial action unit (AU) intensity is an index to characterize human expressions. Accurate AU intensity estimation depends on three major elements: image representation, intensity estimator, and supervisory information. Most existing methods learn intensity estimator with fixed image representation, and rely on the availability of fully annotated supervisory information. In this paper, a novel general framework for AU intensity estimation is presented, which differs from traditional estimation methods in two aspects. First, rather than keeping image representation fixed, it simultaneously learns representation and intensity estimator to achieve an optimal solution. Second, it allows incorporating weak supervisory training signal from human knowledge (e.g. feature smoothness, label smoothness, label ranking, and positive label), which makes our model trainable even fully annotated information is not available. More specifically, human knowledge is represented as either soft or hard constraints which are encoded as regularization terms or equality/inequality constraints, respectively. On top of our novel framework, we additionally propose an efficient algorithm for optimization based on Alternating Direction Method of Multipliers (ADMM). Evaluations on two benchmark databases show that our method outperforms competing methods under different ratios of AU intensity annotations, especially for small ratios.

Deep Convolutional Neural Networks (CNNs) have been pushing the frontier of face recognition over past years. However, existing CNN models are far less accurate when handling partially occluded faces. These general face models generalize poorly for occlusions on variable facial areas. Inspired by the fact that human visual system explicitly ignores the occlusion and only focuses on the non-occluded facial areas, we propose a mask learning strategy to find and discard corrupted feature elements from recognition. A mask dictionary is firstly established by exploiting the differences between the top conv features of occluded and occlusion-free face pairs using innovatively designed pairwise differential siamese network (PDSN). Each item of this dictionary captures the correspondence between occluded facial areas and corrupted feature elements, which is named Feature Discarding Mask (FDM). When dealing with a face image with random partial occlusions, we generate its FDM by combining relevant dictionary items and then multiply it with the original features to eliminate those corrupted feature elements from recognition. Comprehensive experiments on both synthesized and realistic occluded face datasets show that the proposed algorithm significantly outperforms the state-of-the-art systems.

Heterogeneous face recognition (HFR) refers to matching face images acquired from different domains with wide applications in security scenarios. However, HFR is still a challenging problem due to the significant cross-domain discrepancy and the lacking of sufficient training data in different domains. This paper presents a deep neural network approach namely Multi-Margin based Decorrelation Learning (MMDL) to extract decorrelation representations in a hyperspherical space for cross-domain face images. The proposed framework can be divided into two components: heterogeneous representation network and decorrelation representation learning. First, we employ a large scale of accessible visual face images to train heterogeneous representation network. The decorrelation layer projects the output of the first component into decorrelation latent subspace and obtain decorrelation representation. In addition, we design a multi-margin loss (MML), which consists of tetradmargin loss (TML) and heterogeneous angular margin loss (HAML), to constrain the proposed framework. Experimental results on two challenging heterogeneous face databases show that our approach achieves superior performance on both verification and recognition tasks, comparing with state-of-the-art methods.

Despite deep neural networks have demonstrated strong power in face photo-sketch synthesis task, their performance, however, are still limited by the lack of training data (photo-sketch pairs). Knowledge Transfer (KT), which aims at training a smaller and fast student network with the information learned from a larger and accurate teacher network, has attracted much attention recently due to its superior performance in the acceleration and compression of deep neural networks. This work has brought us great inspiration that we can train a relatively small student network on very few training data by transferring knowledge from a larger teacher model trained on enough training data for other tasks. Therefore, we propose a novel knowledge transfer framework to synthesize face photos from face sketches or synthesize face sketches from face photos. Particularly, we utilize two teacher networks trained on large amount of data in related task to learn the knowledge of face photos and face sketches separately and transfer them to two student networks simultaneously. In addition, the two student networks, one for photo ? sketch task and the other for sketch ? photo task, can transfer their knowledge mutually. With the proposed method, we can train our model which has superior performance using a small set of photo-sketch pairs. We validate the effectiveness of our method across several datasets. Quantitative and qualitative evaluations illustrate that our model outperforms other state-of-the-art methods in generating face sketches (or photos) with high visual quality and recognition ability.

HHeterogeneous face recognition (HFR) aims to identify a person from different facial modalities such as visible and near-infrared images. The main challenges of HFR lie in the large modality discrepancy and insufficient training samples. In this paper, we propose the Mutual Component Convolutional Neural Network (MC-CNN), a modal-invariant deep learning framework, to tackle these two issues simultaneously. Our MCCNN incorporates a generative module, i.e. the Mutual Component Analysis (MCA) [1], into modern deep convolutional neural networks by viewing MCA as a special fully-connected (FC) layer. Based on deep features, this FC layer is designed to extract modal-independent hidden factors, and is updated according to maximum likelihood analytic formulation instead of back propagation which prevents over-fitting from limited data naturally. In addition, we develop an MCA loss to update the network for modal-invariant feature learning. Extensive experiments show that our MC-CNN outperforms several finetuned baseline models significantly. Our methods achieve the state-of-the-art performance on CASIA NIR-VIS 2.0, CUHK NIR-VIS and IIIT-D Sketch dataset.

Face recognition has made extraordinary progress owing to the advancement of deep convolutional neural networks (CNNs). The central task of face recognition, including face verification and identification, involves face feature discrimination. However, the traditional softmax loss of deep CNNs usually lacks the power of discrimination. To address this problem, recently several loss functions such as center loss, large margin softmax loss, and angular softmax loss have been proposed. All these improved losses share the same idea: maximizing inter-class variance and minimizing intra-class variance. In this paper, we propose a novel loss function, namely large margin cosine loss (LMCL), to realize this idea from a different perspective. More specifically, we reformulate the softmax loss as a cosine loss by L2 normalizing both features and weight vectors to remove radial variations, based on which a cosine margin term is introduced to further maximize the decision margin in the angular space. As a result, minimum intra-class variance and maximum inter-class variance are achieved by virtue of normalization and cosine decision margin maximization. We refer to our model trained with LMCL as CosFace. Extensive experimental evaluations are conducted on the most popular public-domain face recognition datasets such as MegaFace Challenge, Youtube Faces (YTF) and Labeled Face in the Wild (LFW). We achieve the state-of-the-art performance on these benchmarks, which confirms the effectiveness of our proposed approach.

Recent research endeavors have shown the potential of using feed-forward convolutional neural networks to accomplish fast style transfer for images. In this work, we take one step further to explore the possibility of exploiting a feed-forward network to perform style transfer for videos and simultaneously maintain temporal consistency among stylized video frames. Our feed-forward network is trained by enforcing the outputs of consecutive frames to be both well stylized and temporally consistent. More specifically, a hybrid loss is proposed to capitalize on the content information of input frames, the style information of a given style image, and the temporal information of consecutive frames. To calculate the temporal loss during the training stage, a novel two-frame synergic training mechanism is proposed. Compared with directly applying an existing image style transfer method to videos, our proposed method employs the trained network to yield temporally consistent stylized videos which are much more visually pleasant. In contrast to the prior video style transfer method which relies on time-consuming optimization on the fly, our method runs in real time while generating competitive visual results.

Deep convolutional neural networks have achieved significant improvements on face recognition task due to their ability to learn highly discriminative features from tremendous amounts of face images. Many large scale face datasets exhibit long-tail distribution where a small number of entities (persons) have large number of face images while a large number of persons only have very few face samples (long tail). Most of the existing works alleviate this problem by simply cutting the tailed data and only keep identities with enough number of examples. Unlike these work, this paper investigated how long-tailed data impact the training of face CNNs and develop a novel loss function, called range loss, to effectively utilize the tailed data in training process. More specifically, range loss is designed to reduce overall intrapersonal variations while enlarge interpersonal differences simultaneously. Extensive experiments on two face recognition benchmarks, Labeled Faces in the Wild (LFW) [11] and YouTube Faces (YTF) [33], demonstrate the effectiveness of the proposed range loss in overcoming the long tail effect, and show the good generalization ability of the proposed methods.

Deep Convolutional Neural Networks (CNNs) achieve substantial improvements in face detection in the wild. Classical CNN-based face detection methods simply stack successive layers of filters where an input sample should pass through all layers before reaching a face/non-face decision. Inspired by the fact that for face detection, filters in deeper layers can discriminate between difficult face/non-face samples while those in shallower layers can efficiently reject simple non-face samples, we propose Inside Cascaded Structure that introduces face/non-face classifiers at different layers within the same CNN. In the training phase, we propose data routing mechanism which enables different layers to be trained by different types of samples, and thus deeper layers can focus on handling more difficult samples compared with traditional architecture. In addition, we introduce a two-stream contextual CNN architecture that leverages body part information adaptively to enhance face detection. Extensive experiments on the challenging FD-DB and WIDER FACE benchmarks demonstrate that our method achieves competitive accuracy to the state-of-the-art techniques while keeps real time performance.

Heterogeneous face recognition is an important, yet challenging problem in face recognition community. It refers to matching a probe face image to a gallery of face images taken from alternate imaging modality. The major challenge of heterogeneous face recognition lies in the great discrepancies between different image modalities. Conventional face feature descriptors, e.g., local binary patterns, histogram of oriented gradients, and scale-invariant feature transform, are mostly designed in a handcrafted way and thus generally fail to extract the common discriminant information from the heterogeneous face images. In this paper, we propose a new feature descriptor called common encoding model for heterogeneous face recognition, which is able to capture common discriminant information, such that the large modality gap can be significantly reduced at the feature extraction stage. Specifically, we turn a face image into an encoded one with the encoding model learned from the training data, where the difference of the encoded heterogeneous face images of the same person can be minimized. Based on the encoded face images, we further develop a discriminant matching method to infer the hidden identity information of the cross-modality face images for enhanced recognition performance. The effectiveness of the proposed approach is demonstrated (on several public-domain face datasets) in two typical heterogeneous face recognition scenarios: matching NIR faces to VIS faces and matching sketches to photographs.

Automatic age estimation is an important yet challenging problem. It has many promising applications in social media. Of the existing age estimation algorithms, the personalized approaches are among the most popular ones. However, most person-specific approaches rely heavily on the availability of training images across different ages for a single subject, which is usually difficult to satisfy in practical application of age estimation. To address this limitation, we first propose a new model called Orthogonal Gaussian Process (OGP), which is not restricted by the number of training samples per person. In addition, without sacrifice of discriminative power, OGP is much more computationally efficient than the standard Gaussian Process. Based on OGP, we then develop an effective age estimation approach, namely anisotropic OGP (A-OGP), to further reduce the estimation error. A-OGP is based on an anisotropic noise level learning scheme that contributes to better age estimation performance. To finally optimize the performance of age estimation, we propose a multifeature A-OGP fusion framework that uses multiple features combined with a random sampling method in the feature space. Extensive experiments on several public domain face aging datasets (FG-NET, MORPH Album1, and MORPH Album 2) are conducted to demonstrate the state-of-the-art estimation accuracy of our new algorithms.

While considerable progresses have been made on face recognition, age-invariant face recognition (AIFR) still remains a major challenge in real world applications of face recognition systems. The major difficulty of AIFR arises from the fact that the facial appearance is subject to significant intra-personal changes caused by the aging process over time. In order to address this problem, we propose a novel deep face recognition framework to learn the ageinvariant deep face features through a carefully designed CNN model. To the best of our knowledge, this is the first attempt to show the effectiveness of deep CNNs in advancing the state-of-the-art of AIFR. Extensive experiments are conducted on several public domain face aging datasets (MORPH Album2, FGNET, and CACD-VS) to demonstrate the effectiveness of the proposed model over the state-of the-art. We also verify the excellent generalization of our new model on the famous LFW dataset.

In this letter, we propose an adaptive part-level model knowledge transfer approach for gender classification of facial images based on Fisher vector (FV). Specifically, we first decompose the whole face image into several parts and compute the dense FVs on each face part. An adaptive transfer learning model is then proposed to reduce the discrepancies between the training data and the testing data for enhancing classification performance. Compared to the existing gender classification methods, the proposed approach is more adaptive to the testing data, which is quite beneficial to the performance improvement. Extensive experiments on several public domain face data sets clearly demonstrate the effectiveness of the proposed approach.

Face detection and alignment in unconstrained environment are challenging due to various poses, illuminations, and occlusions. Recent studies show that deep learning approaches can achieve impressive performance on these two tasks. In this letter, we propose a deep cascaded multitask framework that exploits the inherent correlation between detection and alignment to boost up their performance. In particular, our framework leverages a cascaded architecture with three stages of carefully designed deep convolutional networks to predict face and landmark location in a coarse-to-fine manner. In addition, we propose a new online hard sample mining strategy that further improves the performance in practice. Our method achieves superior accuracy over the state-of-the-art techniques on the challenging face detection dataset and benchmark and WIDER FACE benchmarks for face detection, and annotated facial landmarks in the wild benchmark for face alignment, while keeps real-time performance.

Aging face recognition refers to matching the same person's faces across different ages, e.g., matching a person's older face to his (or her) younger one, which has many important practical applications, such as finding missing children. The major challenge of this task is that facial appearance is subject to significant change during the aging process. In this paper, we propose to solve the problem with a hierarchical model based on two-level learning. At the first level, effective features are learned from low-level microstructures, based on our new feature descriptor called local pattern selection (LPS). The proposed LPS descriptor greedily selects low-level discriminant patterns in a way, such that intra-user dissimilarity is minimized. At the second level, higher level visual information is further refined based on the output from the first level. To evaluate the performance of our new method, we conduct extensive experiments on the MORPH data set (the largest face aging data set available in the public domain), which show a significant improvement in accuracy over the state-of-the-art methods.

Heterogeneous face recognition, also known as cross-modality face recognition or intermodality face recognition, refers to matching two face images from alternative image modalities. Since face images from different image modalities of the same person are associated with the same face object, there should be mutual components that reflect those intrinsic face characteristics that are invariant to the image modalities. Motivated by this rationality, we propose a novel approach called Mutual Component Analysis (MCA) to infer the mutual components for robust heterogeneous face recognition. In the MCA approach, a generative model is first proposed to model the process of generating face images in different modalities, and then an Expectation Maximization (EM) algorithm is designed to iteratively learn the model parameters. The learned generative model is able to infer the mutual components (which we call the hidden factor , where hidden means the factor is unreachable and invisible, and can only be inferred from observations) that are associated with the person’s identity, thus enabling fast and effective matching for cross-modality face recognition. To enhance recognition performance, we propose an MCA-based multiclassifier framework using multiple local features. Experimental results show that our new approach significantly outperforms the state-of-the-art results on two typical application scenarios: sketch-to-photo and infrared-to-visible face recognition.

In this paper, we propose a new approach to overcome the representation and matching problems in age invariant face recognition. First, a new maximum entropy feature descriptor (MEFD) is developed that encodes the microstructure of facial images into a set of discrete codes in terms of maximum entropy. By densely sampling the encoded face image, sufficient discriminatory and expressive information can be extracted for further analysis. A new matching method is also developed, called identity factor analysis (IFA), to estimate the probability that two faces have the same underlying identity. The effectiveness of the framework is confirmed by extensive experimentation on two face aging datasets, MORPH (the largest public-domain face aging dataset) and FGNET. We also conduct experiments on the famous LFW dataset to demonstrate the excellent generalizability of our new approach.

Dense feature extraction is becoming increasingly popular in face recognition tasks. Systems based on this approach have demonstrated impressive performance in a range of challenging scenarios. However, improvements in discriminative power come at a computational cost and with a risk of over-fitting. In this paper, we propose a new approach to dense feature extraction for face recognition, which consists of two steps. First, an encoding scheme is devised that compresses high-dimensional dense features into a compact representation by maximizing the intrauser correlation. Second, we develop an adaptive feature matching algorithm for effective classification. This matching method, in contrast to the previous methods, constructs and chooses a small subset of training samples for adaptive matching, resulting in further performance gains. Experiments using several challenging face databases, including labeled Faces in the Wild data set, Morph Album 2, CUHK optical-infrared, and FERET, demonstrate that the proposed approach consistently outperforms the current state of the art.

Age Estimation from facial images has been receiving increasing interest due to its important applications. Among the existing age estimation algorithms, the personalized approaches have been shown to be the most effective ones. However, most of the person-specific approaches (e.g. MTWGP [1], AGES [2], WAS [3]) rely heavily on the availability of training images across different ages for a single subject, which is very difficult to satisfy in practical applications. In order to overcome this problem, we propose a new approach to age estimation, called Orthogonal Gaussian Process (OGP). Compared to standard Gaussian Process, OGP is much more efficient while maintaining the discriminatory power of the standard Gaussian Process. Based on OGP, we further propose an improvement of OGP called anisotropic OGP (A-OGP) to enhance the age estimation performance. Extensive experiments are conducted to demonstrate the state-of-the-art estimation accuracy of our new algorithm on several public-domain face aging datasets: FG-NET face dataset with 82 different subjects, Morph Album 1 dataset with more than 600 subjects, and Morph Album 2 with about 20,000 different subjects.

In biometrics research and industry, it is critical yet a challenge to match infrared face images to optical face images. The major difficulty lies in the fact that a great discrepancy exists between the infrared face image and corresponding optical face image because they are captured by different devices (optical imaging device and infrared imaging device). This paper presents a new approach called common feature discriminant analysis to reduce this great discrepancy and improve optical-infrared face recognition performance. In this approach, a new learning-based face descriptor is first proposed to extract the common features from heterogeneous face images (infrared face images and optical face images), and an effective matching method is then applied to the resulting features to obtain the final decision. Extensive experiments are conducted on two large and challenging optical-infrared face data sets to show the superiority of our approach over the state-of-the-art.

In the Fishervoice (FSH) based framework, the mean supervectors of the speaker models are divided into several subvectors by mixture index. However, this division strategy cannot capture local acoustic class structure information among similar acoustic classes or discriminative information between different acoustic classes. In order to verify whether or not local structure information can help improve system performance, we develop five different speaker supervector segmentation methods. Experiments on NIST SRE08 prove that clustering similar acoustic classes together improves the system performance. In particular, the proposed method of equal size clustering achieves 5.1% relative decrease on EER compared to FSH1.

Age invariant face recognition has received increasing attention due to its great potential in real world applications. In spite of the great progress in face recognition techniques, reliably recognizing faces across ages remains a difficult task. The facial appearance of a person changes substantially over time, resulting in significant intra-class variations. Hence, the key to tackle this problem is to separate the variation caused by aging from the person-specific features that are stable. Specifically, we propose a new method, called Hidden Factor Analysis (HFA). This method captures the intuition above through a probabilistic model with two latent factors: an identity factor that is age-invariant and an age factor affected by the aging process. Then, the observed appearance can be modeled as a combination of the components generated based on these factors. We also develop a learning algorithm that jointly estimates the latent factors and the model parameters using an EM procedure. Extensive experiments on two well-known public domain face aging datasets: MORPH (the largest public face aging database) and FGNET, clearly show that the proposed method achieves notable improvement over state-of-the-art algorithms.

Automatic face photo-sketch image retrieval has attracted great attention in recent years due to its important applications in real life. The major difficulty in automatic face photo-sketch image retrieval lies in the fact that there exists great discrepancy between the different image modalities (photo and sketch). In order to reduce such discrepancy and improve the performance of automatic face photo-sketch image retrieval, we propose a new framework called multi-feature canonical correlation analysis (MCCA) to effectively address this problem. The MCCA is an extension and improvement of the canonical correlation analysis (CCA) algorithmusing multiple features combined with two different random sampling methods in feature space and sample space. In this framework, we first represent each photo or sketch using a patch-based local feature representation scheme, in which histograms of oriented gradients (HOG) and multi-scale local binary pattern (MLBP) serve as the local descriptors. Canonical correlation analysis (CCA) is then performed on a collection of random subspaces to construct an ensemble of classifiers for photo-sketch image retrieval. Extensive experiments on two public-domain face photo-sketch datasets (CUFS and CUFSF) clearly show that the proposed approach obtains a substantial improvement over the state-of-the-art.

Using Joint Factor Analysis (JFA) supervector for subspace analysis has many problems, such as high processing complexity and over-fitting. We propose an analysis framework based on random subspace sampling to address these problems. In this framework, JFA supervectors are first partitioned equally and each partitioned subvector is projected on to a subspace by PCA. All projected subvectors are then concatenated and PCA is applied again to reduce the dimension by projection onto a low-dimensional feature space. Finally, we randomly sample this feature space and build classifiers for the sampled features. The classifiers are fused to produce the final classification output. Experiments on NIST SRE08 prove the effectiveness of the proposed framework.

The problem of matching a forensic sketch to a gallery of mug shot images is addressed in this paper. Previous research in sketch matching only offered solutions to matching highly accurate sketches that were drawn while looking at the subject (viewed sketches). Forensic sketches differ from viewed sketches in that they are drawn by a police sketch artist using the description of the subject provided by an eyewitness. To identify forensic sketches, we present a framework called local feature-based discriminant analysis (LFDA). In LFDA, we individually represent both sketches and photos using SIFT feature descriptors and multiscale local binary patterns (MLBP). Multiple discriminant projections are then used on partitioned vectors of the feature-based representation for minimum distance matching. We apply this method to match a data set of 159 forensic sketches against a mug shot gallery containing 10,159 images. Compared to a leading commercial face recognition system, LFDA offers substantial improvements in matching forensic sketches to the corresponding face images. We were able to further improve the matching performance using race and gender information to reduce the target gallery size. Additional experiments demonstrate that the proposed framework leads to state-of-the-art accuracys when matching viewed sketches.

Aging variation poses a serious problem to automatic face recognition systems. Most of the face recognition studies that have addressed the aging problem are focused on age estimation or aging simulation. Designing an appropriate feature representation and an effective matching framework for age invariant face recognition remains an open problem. In this paper, we propose a discriminative model to address face matching in the presence of age variation. In this framework, we first represent each face by designing a densely sampled local feature description scheme, in which scale invariant feature transform (SIFT) and multi-scale local binary patterns (MLBP) serve as the local descriptors. By densely sampling the two kinds of local descriptors from the entire facial image, sufficient discriminatory information, including the distribution of the edge direction in the face image (that is expected to be age invariant) can be extracted for further analysis. Since both SIFT-based local features and MLBP-based local features span a high-dimensional feature space, to avoid the overfitting problem, we develop an algorithm, called multi-feature discriminant analysis (MFDA) to process these two local feature spaces in a unified framework. The MFDA is an extension and improvement of the LDA using multiple features combined with two different random sampling methods in feature and sample space. By random sampling the training set as well as the feature space, multiple LDA-based classifiers are constructed and then combined to generate a robust decision via a fusion rule. Experimental results show that our approach outperforms a state-of-the-art commercial face recognition engine on two public domain face aging data sets: MORPH and FG-NET. We also compare the performance of the proposed discriminative model with a generative aging model. A fusion of discriminative and generative models further improves the face matching accuracy in the presence of aging.

We propose a new framework for speaker recognition, referred as Fishervoice. It includes the design of a feature representation known as the structured score vector (SSV), which relates acoustic structures with “key” frames in an input utterance in capturing relevant speaker characteristics. The framework also applies nonparametric Fisher's discriminant analysis to map the SSVs into a compressed discriminant subspace, where matching is performed between a test sample and reference speaker samples to achieve speaker recognition. The objective is to reduce intra-speaker variability and emphasize discriminative class boundary information to facilitate speaker recognition. Experiments based on the XM2VTSDB corpus shows that the Fishervoice framework gave superior performance, compared with other commonly used approaches, e.g. GMM-UBM and Eigenvoice.

In this paper, we develop a new framework for face recognition based on nonparametric discriminant analysis (NDA) and multi-classifier integration. Traditional LDA-based methods suffer a fundamental limitation originating from the parametric nature of scatter matrices, which are based on the Gaussian distribution assumption. The performance of these methods notably degrades when the actual distribution is Non-Gaussian. To address this problem, we propose a new formulation of scatter matrices to extend the two-class nonparametric discriminant analysis to multi-class cases. Then, we develop two more improved multi-class NDA-based algorithms (NSA and NFA) with each one having two complementary methods based on the principal space and the null space of the intra-class scatter matrix respectively. Comparing to the NSA, the NFA is more effective in the utilization of the classification boundary information. In order to exploit the complementary nature of the two kinds of NFA (PNFA and NNFA), we finally develop a dual NFA-based multi-classifier fusion framework by employing the over complete Gabor representation to boost the recognition performance. We show the improvements of the developed new algorithms over the traditional subspace methods through comparative experiments on two challenging face databases, Purdue AR database and XM2VTS database.

In this paper, we develop a new video-to-video face recognition algorithm. The major advantage of the video-based method is that more information is available in a video sequence than in a single image. In order to take advantage of the large amount of information in the video sequence and at the same time overcome the processing speed and data size problems, we develop several new techniques including temporal and spatial frame synchronization, multilevel discriminant subspace analysis, and multiclassifier integration for video sequence processing. An aligned video sequence for each person is first obtained by applying temporal and spatial synchronization, which effectively establishes the face correspondence using both audio and video information; then multilevel discriminant subspace analysis or multiclassifier integration is employed for further analysis based on the synchronized sequence. The method preserves most of the temporal-spatial information contained in a video sequence. Extensive experiments on the XM2VTS database clearly show the superiority of our new algorithms with near-perfect classification results (99.3%) obtained.

Outdoor face recognition is among the most challenging problems for face recognition. In this paper, we develop a discriminant mutual subspace learning algorithm for indoor and outdoor face recognition. Unlike traditional algorithms using one subspace to model both indoor and outdoor face images, our algorithm simultaneously learn two related subspaces for indoor and outdoor images respectively thus can better model both. To further improve the recognition performance we develop a DMSL-based multi-classifier fusion framework on Gabor images using a new fusion method called adaptive informative fusion scheme. Experimental results clearly show that this framework can greatly enhance the recognition performance.

In this paper, we first develop a direct Bayesian-based support vector machine (SVM) by combining the Bayesian analysis with the SVM. Unlike traditional SVM-based face recognition methods that require one to train a large number of SVMs, the direct Bayesian SVM needs only one SVM trained to classify the face difference between intrapersonal variation and extrapersonal variation. However, the additional simplicity means that the method has to separate two complex subspaces by one hyperplane thus affecting the recognition accuracy. In order to improve the recognition performance, we develop three more Bayesian-based SVMs, including the one-versus-all method, the hierarchical agglomerative clustering-based method, and the adaptive clustering method. Finally, we combine the adaptive clustering method with multilevel subspace analysis to further improve the recognition performance. We show the improvement of the new algorithms over traditional subspace methods through experiments on two face databases - the FERET database and the XM2VTS database

Linear discriminant analysis (LDA) is a popular face recognition technique. However, an inherent problem with this technique stems from the parametric nature of the scatter matrix, in which the sample distribution in each class is assumed to be normal distribution. So it tends to suffer in the case of non-normal distribution. In this paper a nonparametric scatter matrix is defined to replace the traditional parametric scatter matrix in order to overcome this problem. Two kinds of nonparametric subspace analysis (NSA): PNSA and NNSA are proposed for face recognition. The former is based on the principal space of intra-personal scatter matrix, while the latter is based on the null space. In addition, based on the complementary nature of PNSA and NNSA, we further develop a dual NSA-based classifier framework using Gabor images to further improve the recognition performance. Experiments achieve near perfect recognition accuracy (99.7%) on the XM2VTS database.