Abstract:Face Forgery videos have elicited critical social public concerns and various detectors have been proposed. However, fully-supervised detectors may lead to easily overfitting to specific forgery methods or videos, and existing self-supervised detectors are strict on auxiliary tasks, such as requiring audio or multi-modalities, leading to limited generalization and robustness. In this paper, we examine whether we can address this issue by leveraging visual-only real face videos. To this end, we propose to learn the Natural Consistency representation (NACO) of real face videos in a self-supervised manner, which is inspired by the observation that fake videos struggle to maintain the natural spatiotemporal consistency even under unknown forgery methods and different perturbations. Our NACO first extracts spatial features of each frame by CNNs then integrates them into Transformer to learn the long-range spatiotemporal representation, leveraging the advantages of CNNs and Transformer on local spatial receptive field and long-term memory respectively. Furthermore, a Spatial Predictive Module~(SPM) and a Temporal Contrastive Module~(TCM) are introduced to enhance the natural consistency representation learning. The SPM aims to predict random masked spatial features from spatiotemporal representation, and the TCM regularizes the latent distance of spatiotemporal representation by shuffling the natural order to disturb the consistency, which could both force our NACO more sensitive to the natural spatiotemporal consistency. After the representation learning stage, a MLP head is fine-tuned to perform the usual forgery video classification task. Extensive experiments show that our method outperforms other state-of-the-art competitors with impressive generalization and robustness.
Abstract:Dataset condensation addresses the problem of data burden by learning a small synthetic training set that preserves essential knowledge from the larger real training set. To date, the state-of-the-art (SOTA) results are often yielded by optimization-oriented methods, but their inefficiency hinders their application to realistic datasets. On the other hand, the Distribution-Matching (DM) methods show remarkable efficiency but sub-optimal results compared to optimization-oriented methods. In this paper, we reveal the limitations of current DM-based methods from the inner-class and inter-class views, i.e., Persistent Training and Distribution Shift. To address these problems, we propose a new DM-based method named Dual-view distribution AligNment for dataset CondEnsation (DANCE), which exploits a few pre-trained models to improve DM from both inner-class and inter-class views. Specifically, from the inner-class view, we construct multiple "middle encoders" to perform pseudo long-term distribution alignment, making the condensed set a good proxy of the real one during the whole training process; while from the inter-class view, we use the expert models to perform distribution calibration, ensuring the synthetic data remains in the real class region during condensing. Experiments demonstrate the proposed method achieves a SOTA performance while maintaining comparable efficiency with the original DM across various scenarios. Source codes are available at https://github.com/Hansong-Zhang/DANCE.
Abstract:Masked face recognition is important for social good but challenged by diverse occlusions that cause insufficient or inaccurate representations. In this work, we propose a unified deep network to learn generative-to-discriminative representations for facilitating masked face recognition. To this end, we split the network into three modules and learn them on synthetic masked faces in a greedy module-wise pretraining manner. First, we leverage a generative encoder pretrained for face inpainting and finetune it to represent masked faces into category-aware descriptors. Attribute to the generative encoder's ability in recovering context information, the resulting descriptors can provide occlusion-robust representations for masked faces, mitigating the effect of diverse masks. Then, we incorporate a multi-layer convolutional network as a discriminative reformer and learn it to convert the category-aware descriptors into identity-aware vectors, where the learning is effectively supervised by distilling relation knowledge from off-the-shelf face recognition model. In this way, the discriminative reformer together with the generative encoder serves as the pretrained backbone, providing general and discriminative representations towards masked faces. Finally, we cascade one fully-connected layer following by one softmax layer into a feature classifier and finetune it to identify the reformed identity-aware vectors. Extensive experiments on synthetic and realistic datasets demonstrate the effectiveness of our approach in recognizing masked faces.
Abstract:Training state-of-the-art (SOTA) deep models often requires extensive data, resulting in substantial training and storage costs. To address these challenges, dataset condensation has been developed to learn a small synthetic set that preserves essential information from the original large-scale dataset. Nowadays, optimization-oriented methods have been the primary method in the field of dataset condensation for achieving SOTA results. However, the bi-level optimization process hinders the practical application of such methods to realistic and larger datasets. To enhance condensation efficiency, previous works proposed Distribution-Matching (DM) as an alternative, which significantly reduces the condensation cost. Nonetheless, current DM-based methods have yielded less comparable results to optimization-oriented methods due to their focus on aligning only the first moment of the distributions. In this paper, we present a novel DM-based method named M3D for dataset condensation by Minimizing the Maximum Mean Discrepancy between feature representations of the synthetic and real images. By embedding their distributions in a reproducing kernel Hilbert space, we align all orders of moments of the distributions of real and synthetic images, resulting in a more generalized condensed set. Notably, our method even surpasses the SOTA optimization-oriented method IDC on the high-resolution ImageNet dataset. Extensive analysis is conducted to verify the effectiveness of the proposed method.
Abstract:As the size of the datasets getting larger, accurately annotating such datasets is becoming more impractical due to the expensiveness on both time and economy. Therefore, crowd-sourcing has been widely adopted to alleviate the cost of collecting labels, which also inevitably introduces label noise and eventually degrades the performance of the model. To learn from crowd-sourcing annotations, modeling the expertise of each annotator is a common but challenging paradigm, because the annotations collected by crowd-sourcing are usually highly-sparse. To alleviate this problem, we propose Coupled Confusion Correction (CCC), where two models are simultaneously trained to correct the confusion matrices learned by each other. Via bi-level optimization, the confusion matrices learned by one model can be corrected by the distilled data from the other. Moreover, we cluster the ``annotator groups'' who share similar expertise so that their confusion matrices could be corrected together. In this way, the expertise of the annotators, especially of those who provide seldom labels, could be better captured. Remarkably, we point out that the annotation sparsity not only means the average number of labels is low, but also there are always some annotators who provide very few labels, which is neglected by previous works when constructing synthetic crowd-sourcing annotations. Based on that, we propose to use Beta distribution to control the generation of the crowd-sourcing labels so that the synthetic annotations could be more consistent with the real-world ones. Extensive experiments are conducted on two types of synthetic datasets and three real-world datasets, the results of which demonstrate that CCC significantly outperforms state-of-the-art approaches.
Abstract:Noisy multi-label learning has garnered increasing attention due to the challenges posed by collecting large-scale accurate labels, making noisy labels a more practical alternative. Motivated by noisy multi-class learning, the introduction of transition matrices can help model multi-label noise and enable the development of statistically consistent algorithms for noisy multi-label learning. However, estimating multi-label noise transition matrices remains a challenging task, as most existing estimators in noisy multi-class learning rely on anchor points and accurate fitting of noisy class posteriors, which is hard to satisfy in noisy multi-label learning. In this paper, we address this problem by first investigating the identifiability of class-dependent transition matrices in noisy multi-label learning. Building upon the identifiability results, we propose a novel estimator that leverages label correlations without the need for anchor points or precise fitting of noisy class posteriors. Specifically, we first estimate the occurrence probability of two noisy labels to capture noisy label correlations. Subsequently, we employ sample selection techniques to extract information implying clean label correlations, which are then used to estimate the occurrence probability of one noisy label when a certain clean label appears. By exploiting the mismatches in label correlations implied by these occurrence probabilities, we demonstrate that the transition matrix becomes identifiable and can be acquired by solving a bilinear decomposition problem. Theoretically, we establish an estimation error bound for our multi-label transition matrix estimator and derive a generalization error bound for our statistically consistent algorithm. Empirically, we validate the effectiveness of our estimator in estimating multi-label noise transition matrices, leading to excellent classification performance.
Abstract:Face forgery videos have caused severe social public concern, and various detectors have been proposed recently. However, most of them are trained in a supervised manner with limited generalization when detecting videos from different forgery methods or real source videos. To tackle this issue, we explore to take full advantage of the difference between real and forgery videos by only exploring the common representation of real face videos. In this paper, a Self-supervised Transformer cooperating with Contrastive and Reconstruction learning (CoReST) is proposed, which is first pre-trained only on real face videos in a self-supervised manner, and then fine-tuned a linear head on specific face forgery video datasets. Two specific auxiliary tasks incorporated contrastive and reconstruction learning are designed to enhance the representation learning. Furthermore, a Domain Adaptive Reconstruction (DAR) module is introduced to bridge the gap between different forgery domains by reconstructing on unlabeled target videos when fine-tuning. Extensive experiments on public datasets demonstrate that our proposed method performs even better than the state-of-the-art supervised competitors with impressive generalization.
Abstract:Learning from crowds describes that the annotations of training data are obtained with crowd-sourcing services. Multiple annotators each complete their own small part of the annotations, where labeling mistakes that depend on annotators occur frequently. Modeling the label-noise generation process by the noise transition matrix is a power tool to tackle the label noise. In real-world crowd-sourcing scenarios, noise transition matrices are both annotator- and instance-dependent. However, due to the high complexity of annotator- and instance-dependent transition matrices (AIDTM), \textit{annotation sparsity}, which means each annotator only labels a little part of instances, makes modeling AIDTM very challenging. Prior works simplify the problem by assuming the transition matrix is instance-independent or using simple parametric way, while lose modeling generality. Motivated by this, we target a more realistic problem, estimating general AIDTM in practice. Without losing modeling generality, we parameterize AIDTM with deep neural networks. To alleviate the modeling challenge, we suppose every annotator shares its noise pattern with similar annotators, and estimate AIDTM via \textit{knowledge transfer}. We hence first model the mixture of noise patterns by all annotators, and then transfer this modeling to individual annotators. Furthermore, considering that the transfer from the mixture of noise patterns to individuals may cause two annotators with highly different noise generations to perturb each other, we employ the knowledge transfer between identified neighboring annotators to calibrate the modeling. Experiments confirm the superiority of the proposed approach on synthetic and real-world crowd-sourcing data. Source codes will be released.
Abstract:A number of deep models trained on high-quality and valuable images have been deployed in practical applications, which may pose a leakage risk of data privacy. Learning differentially private generative models can sidestep this challenge through indirect data access. However, such differentially private generative models learned by existing approaches can only generate images with a low-resolution of less than 128x128, hindering the widespread usage of generated images in downstream training. In this work, we propose learning differentially private probabilistic models (DPPM) to generate high-resolution images with differential privacy guarantee. In particular, we first train a model to fit the distribution of the training data and make it satisfy differential privacy by performing a randomized response mechanism during training process. Then we perform Hamiltonian dynamics sampling along with the differentially private movement direction predicted by the trained probabilistic model to obtain the privacy-preserving images. In this way, it is possible to apply these images to different downstream tasks while protecting private information. Notably, compared to other state-of-the-art differentially private generative approaches, our approach can generate images up to 256x256 with remarkable visual quality and data utility. Extensive experiments show the effectiveness of our approach.
Abstract:While the abuse of deepfake technology has caused serious concerns recently, how to detect deepfake videos is still a challenge due to the high photo-realistic synthesis of each frame. Existing image-level approaches often focus on single frame and ignore the spatiotemporal cues hidden in deepfake videos, resulting in poor generalization and robustness. The key of a video-level detector is to fully exploit the spatiotemporal inconsistency distributed in local facial regions across different frames in deepfake videos. Inspired by that, this paper proposes a simple yet effective patch-level approach to facilitate deepfake video detection via spatiotemporal dropout transformer. The approach reorganizes each input video into bag of patches that is then fed into a vision transformer to achieve robust representation. Specifically, a spatiotemporal dropout operation is proposed to fully explore patch-level spatiotemporal cues and serve as effective data augmentation to further enhance model's robustness and generalization ability. The operation is flexible and can be easily plugged into existing vision transformers. Extensive experiments demonstrate the effectiveness of our approach against 25 state-of-the-arts with impressive robustness, generalizability, and representation ability.