Jue Wang

Zhan Tong, Yibing Song, Jue Wang et al.

Pre-training video transformers on extra large-scale datasets is generally required to achieve premier performance on relatively small datasets. In this paper, we show that video masked autoencoders (VideoMAE) are data-efficient learners for self-supervised video pre-training (SSVP). We are inspired by the recent ImageMAE and propose customized video tube masking with an extremely high ratio. This simple design makes video reconstruction a more challenging self-supervision task, thus encouraging extracting more effective video representations during this pre-training process. We obtain three important findings on SSVP: (1) An extremely high proportion of masking ratio (i.e., 90% to 95%) still yields favorable performance of VideoMAE. The temporally redundant video content enables a higher masking ratio than that of images. (2) VideoMAE achieves impressive results on very small datasets (i.e., around 3k-4k videos) without using any extra data. (3) VideoMAE shows that data quality is more important than data quantity for SSVP. Domain shift between pre-training and target datasets is an important issue. Notably, our VideoMAE with the vanilla ViT can achieve 87.4% on Kinetics-400, 75.4% on Something-Something V2, 91.3% on UCF101, and 62.6% on HMDB51, without using any extra data. Code is available at https://github.com/MCG-NJU/VideoMAE.

Weihuang Liu, Xiaodong Cun, Chi-Man Pun et al. · tsinghua

Image inpainting aims to fill the missing hole of the input. It is hard to solve this task efficiently when facing high-resolution images due to two reasons: (1) Large reception field needs to be handled for high-resolution image inpainting. (2) The general encoder and decoder network synthesizes many background pixels synchronously due to the form of the image matrix. In this paper, we try to break the above limitations for the first time thanks to the recent development of continuous implicit representation. In detail, we down-sample and encode the degraded image to produce the spatial-adaptive parameters for each spatial patch via an attentional Fast Fourier Convolution(FFC)-based parameter generation network. Then, we take these parameters as the weights and biases of a series of multi-layer perceptron(MLP), where the input is the encoded continuous coordinates and the output is the synthesized color value. Thanks to the proposed structure, we only encode the high-resolution image in a relatively low resolution for larger reception field capturing. Then, the continuous position encoding will be helpful to synthesize the photo-realistic high-frequency textures by re-sampling the coordinate in a higher resolution. Also, our framework enables us to query the coordinates of missing pixels only in parallel, yielding a more efficient solution than the previous methods. Experiments show that the proposed method achieves real-time performance on the 2048$\times$2048 images using a single GTX 2080 Ti GPU and can handle 4096$\times$4096 images, with much better performance than existing state-of-the-art methods visually and numerically. The code is available at: https://github.com/NiFangBaAGe/CoordFill.

Shoufa Chen, Chongjian Ge, Zhan Tong et al.

Pretraining Vision Transformers (ViTs) has achieved great success in visual recognition. A following scenario is to adapt a ViT to various image and video recognition tasks. The adaptation is challenging because of heavy computation and memory storage. Each model needs an independent and complete finetuning process to adapt to different tasks, which limits its transferability to different visual domains. To address this challenge, we propose an effective adaptation approach for Transformer, namely AdaptFormer, which can adapt the pre-trained ViTs into many different image and video tasks efficiently. It possesses several benefits more appealing than prior arts. Firstly, AdaptFormer introduces lightweight modules that only add less than 2% extra parameters to a ViT, while it is able to increase the ViT's transferability without updating its original pre-trained parameters, significantly outperforming the existing 100\% fully fine-tuned models on action recognition benchmarks. Secondly, it can be plug-and-play in different Transformers and scalable to many visual tasks. Thirdly, extensive experiments on five image and video datasets show that AdaptFormer largely improves ViTs in the target domains. For example, when updating just 1.5% extra parameters, it achieves about 10% and 19% relative improvement compared to the fully fine-tuned models on Something-Something~v2 and HMDB51, respectively. Code is available at https://github.com/ShoufaChen/AdaptFormer.

Liang Chen, Yong Zhang, Yibing Song et al.

Recent studies in deepfake detection have yielded promising results when the training and testing face forgeries are from the same dataset. However, the problem remains challenging when one tries to generalize the detector to forgeries created by unseen methods in the training dataset. This work addresses the generalizable deepfake detection from a simple principle: a generalizable representation should be sensitive to diverse types of forgeries. Following this principle, we propose to enrich the "diversity" of forgeries by synthesizing augmented forgeries with a pool of forgery configurations and strengthen the "sensitivity" to the forgeries by enforcing the model to predict the forgery configurations. To effectively explore the large forgery augmentation space, we further propose to use the adversarial training strategy to dynamically synthesize the most challenging forgeries to the current model. Through extensive experiments, we show that the proposed strategies are surprisingly effective (see Figure 1), and they could achieve superior performance than the current state-of-the-art methods. Code is available at \url{https://github.com/liangchen527/SLADD}.

Xiaojun Jia, Yong Zhang, Baoyuan Wu et al.

Adversarial training (AT) is always formulated as a minimax problem, of which the performance depends on the inner optimization that involves the generation of adversarial examples (AEs). Most previous methods adopt Projected Gradient Decent (PGD) with manually specifying attack parameters for AE generation. A combination of the attack parameters can be referred to as an attack strategy. Several works have revealed that using a fixed attack strategy to generate AEs during the whole training phase limits the model robustness and propose to exploit different attack strategies at different training stages to improve robustness. But those multi-stage hand-crafted attack strategies need much domain expertise, and the robustness improvement is limited. In this paper, we propose a novel framework for adversarial training by introducing the concept of "learnable attack strategy", dubbed LAS-AT, which learns to automatically produce attack strategies to improve the model robustness. Our framework is composed of a target network that uses AEs for training to improve robustness and a strategy network that produces attack strategies to control the AE generation. Experimental evaluations on three benchmark databases demonstrate the superiority of the proposed method. The code is released at https://github.com/jiaxiaojunQAQ/LAS-AT.

Zeyu Qin, Yanbo Fan, Yi Liu et al.

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work, we study the transferability of adversarial examples, which is significant due to its threat to real-world applications where model architecture or parameters are usually unknown. Many existing works reveal that the adversarial examples are likely to overfit the surrogate model that they are generated from, limiting its transfer attack performance against different target models. To mitigate the overfitting of the surrogate model, we propose a novel attack method, dubbed reverse adversarial perturbation (RAP). Specifically, instead of minimizing the loss of a single adversarial point, we advocate seeking adversarial example located at a region with unified low loss value, by injecting the worst-case perturbation (the reverse adversarial perturbation) for each step of the optimization procedure. The adversarial attack with RAP is formulated as a min-max bi-level optimization problem. By integrating RAP into the iterative process for attacks, our method can find more stable adversarial examples which are less sensitive to the changes of decision boundary, mitigating the overfitting of the surrogate model. Comprehensive experimental comparisons demonstrate that RAP can significantly boost adversarial transferability. Furthermore, RAP can be naturally combined with many existing black-box attack techniques, to further boost the transferability. When attacking a real-world image recognition system, Google Cloud Vision API, we obtain 22% performance improvement of targeted attacks over the compared method. Our codes are available at https://github.com/SCLBD/Transfer_attack_RAP.

Xiaojun Jia, Yong Zhang, Xingxing Wei et al.

Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e.,the robust accuracy against adversarial attacks suddenly and dramatically decreases. Though several FAT variants spare no effort to prevent overfitting, they sacrifice much calculation cost. In this paper, we explore the difference between the training processes of SAT and FAT and observe that the attack success rate of adversarial examples (AEs) of FAT gets worse gradually in the late training stage, resulting in overfitting. The AEs are generated by the fast gradient sign method (FGSM) with a zero or random initialization. Based on the observation, we propose a prior-guided FGSM initialization method to avoid overfitting after investigating several initialization strategies, improving the quality of the AEs during the whole training process. The initialization is formed by leveraging historically generated AEs without additional calculation cost. We further provide a theoretical analysis for the proposed initialization method. We also propose a simple yet effective regularizer based on the prior-guided initialization,i.e., the currently generated perturbation should not deviate too much from the prior-guided initialization. The regularizer adopts both historical and current adversarial perturbations to guide the model learning. Evaluations on four datasets demonstrate that the proposed method can prevent catastrophic overfitting and outperform state-of-the-art FAT methods. The code is released at https://github.com/jiaxiaojunQAQ/FGSM-PGI.

Jiaxu Zhang, Junwu Weng, Di Kang et al.

A good motion retargeting cannot be reached without reasonable consideration of source-target differences on both the skeleton and shape geometry levels. In this work, we propose a novel Residual RETargeting network (R2ET) structure, which relies on two neural modification modules, to adjust the source motions to fit the target skeletons and shapes progressively. In particular, a skeleton-aware module is introduced to preserve the source motion semantics. A shape-aware module is designed to perceive the geometries of target characters to reduce interpenetration and contact-missing. Driven by our explored distance-based losses that explicitly model the motion semantics and geometry, these two modules can learn residual motion modifications on the source motion to generate plausible retargeted motion in a single inference without post-processing. To balance these two modifications, we further present a balancing gate to conduct linear interpolation between them. Extensive experiments on the public dataset Mixamo demonstrate that our R2ET achieves the state-of-the-art performance, and provides a good balance between the preservation of motion semantics as well as the attenuation of interpenetration and contact-missing. Code is available at https://github.com/Kebii/R2ET.

Zhengdi Yu, Shaoli Huang, Chen Fang et al.

Reconstructing two hands from monocular RGB images is challenging due to frequent occlusion and mutual confusion. Existing methods mainly learn an entangled representation to encode two interacting hands, which are incredibly fragile to impaired interaction, such as truncated hands, separate hands, or external occlusion. This paper presents ACR (Attention Collaboration-based Regressor), which makes the first attempt to reconstruct hands in arbitrary scenarios. To achieve this, ACR explicitly mitigates interdependencies between hands and between parts by leveraging center and part-based attention for feature extraction. However, reducing interdependence helps release the input constraint while weakening the mutual reasoning about reconstructing the interacting hands. Thus, based on center attention, ACR also learns cross-hand prior that handle the interacting hands better. We evaluate our method on various types of hand reconstruction datasets. Our method significantly outperforms the best interacting-hand approaches on the InterHand2.6M dataset while yielding comparable performance with the state-of-the-art single-hand methods on the FreiHand dataset. More qualitative results on in-the-wild and hand-object interaction datasets and web images/videos further demonstrate the effectiveness of our approach for arbitrary hand reconstruction. Our code is available at https://github.com/ZhengdiYu/Arbitrary-Hands-3D-Reconstruction.

Kun Cheng, Xiaodong Cun, Yong Zhang et al. · tsinghua

We present VideoReTalking, a new system to edit the faces of a real-world talking head video according to input audio, producing a high-quality and lip-syncing output video even with a different emotion. Our system disentangles this objective into three sequential tasks: (1) face video generation with a canonical expression; (2) audio-driven lip-sync; and (3) face enhancement for improving photo-realism. Given a talking-head video, we first modify the expression of each frame according to the same expression template using the expression editing network, resulting in a video with the canonical expression. This video, together with the given audio, is then fed into the lip-sync network to generate a lip-syncing video. Finally, we improve the photo-realism of the synthesized faces through an identity-aware face enhancement network and post-processing. We use learning-based approaches for all three steps and all our modules can be tackled in a sequential pipeline without any user intervention. Furthermore, our system is a generic approach that does not need to be retrained to a specific person. Evaluations on two widely-used datasets and in-the-wild examples demonstrate the superiority of our framework over other state-of-the-art methods in terms of lip-sync accuracy and visual quality.

Mingdeng Cao, Yanbo Fan, Yong Zhang et al.

Video deblurring is still an unsolved problem due to the challenging spatio-temporal modeling process. While existing convolutional neural network-based methods show a limited capacity for effective spatial and temporal modeling for video deblurring. This paper presents VDTR, an effective Transformer-based model that makes the first attempt to adapt Transformer for video deblurring. VDTR exploits the superior long-range and relation modeling capabilities of Transformer for both spatial and temporal modeling. However, it is challenging to design an appropriate Transformer-based model for video deblurring due to the complicated non-uniform blurs, misalignment across multiple frames and the high computational costs for high-resolution spatial modeling. To address these problems, VDTR advocates performing attention within non-overlapping windows and exploiting the hierarchical structure for long-range dependencies modeling. For frame-level spatial modeling, we propose an encoder-decoder Transformer that utilizes multi-scale features for deblurring. For multi-frame temporal modeling, we adapt Transformer to fuse multiple spatial features efficiently. Compared with CNN-based methods, the proposed method achieves highly competitive results on both synthetic and real-world video deblurring benchmarks, including DVD, GOPRO, REDS and BSD. We hope such a Transformer-based architecture can serve as a powerful alternative baseline for video deblurring and other video restoration tasks. The source code will be available at \url{https://github.com/ljzycmd/VDTR}.

Yiming Zhu, Hongyu Liu, Yibing Song et al.

Free-form text prompts allow users to describe their intentions during image manipulation conveniently. Based on the visual latent space of StyleGAN[21] and text embedding space of CLIP[34], studies focus on how to map these two latent spaces for text-driven attribute manipulations. Currently, the latent mapping between these two spaces is empirically designed and confines that each manipulation model can only handle one fixed text prompt. In this paper, we propose a method named Free-Form CLIP (FFCLIP), aiming to establish an automatic latent mapping so that one manipulation model handles free-form text prompts. Our FFCLIP has a cross-modality semantic modulation module containing semantic alignment and injection. The semantic alignment performs the automatic latent mapping via linear transformations with a cross attention mechanism. After alignment, we inject semantics from text prompt embeddings to the StyleGAN latent space. For one type of image (e.g., `human portrait'), one FFCLIP model can be learned to handle free-form text prompts. Meanwhile, we observe that although each training text prompt only contains a single semantic meaning, FFCLIP can leverage text prompts with multiple semantic meanings for image manipulation. In the experiments, we evaluate FFCLIP on three types of images (i.e., `human portraits', `cars', and `churches'). Both visual and numerical results show that FFCLIP effectively produces semantically accurate and visually realistic images. Project page: https://github.com/KumapowerLIU/FFCLIP.

Can Zhang, Tianyu Yang, Junwu Weng et al.

Unsupervised video representation learning has made remarkable achievements in recent years. However, most existing methods are designed and optimized for video classification. These pre-trained models can be sub-optimal for temporal localization tasks due to the inherent discrepancy between video-level classification and clip-level localization. To bridge this gap, we make the first attempt to propose a self-supervised pretext task, coined as Pseudo Action Localization (PAL) to Unsupervisedly Pre-train feature encoders for Temporal Action Localization tasks (UP-TAL). Specifically, we first randomly select temporal regions, each of which contains multiple clips, from one video as pseudo actions and then paste them onto different temporal positions of the other two videos. The pretext task is to align the features of pasted pseudo action regions from two synthetic videos and maximize the agreement between them. Compared to the existing unsupervised video representation learning approaches, our PAL adapts better to downstream TAL tasks by introducing a temporal equivariant contrastive learning paradigm in a temporally dense and scale-aware manner. Extensive experiments show that PAL can utilize large-scale unlabeled video data to significantly boost the performance of existing TAL methods. Our codes and models will be made publicly available at https://github.com/zhang-can/UP-TAL.

Jue Wang, Binhang Yuan, Luka Rimanic et al. · eth-zurich

Communication compression is a crucial technique for modern distributed learning systems to alleviate their communication bottlenecks over slower networks. Despite recent intensive studies of gradient compression for data parallel-style training, compressing the activations for models trained with pipeline parallelism is still an open problem. In this paper, we propose AC-SGD, a novel activation compression algorithm for communication-efficient pipeline parallelism training over slow networks. Different from previous efforts in activation compression, instead of compressing activation values directly, AC-SGD compresses the changes of the activations. This allows us to show, to the best of our knowledge for the first time, that one can still achieve $O(1/\sqrt{T})$ convergence rate for non-convex objectives under activation compression, without making assumptions on gradient unbiasedness that do not hold for deep learning models with non-linear activation functions.We then show that AC-SGD can be optimized and implemented efficiently, without additional end-to-end runtime overhead.We evaluated AC-SGD to fine-tune language models with up to 1.5 billion parameters, compressing activations to 2-4 bits.AC-SGD provides up to 4.3X end-to-end speed-up in slower networks, without sacrificing model quality. Moreover, we also show that AC-SGD can be combined with state-of-the-art gradient compression algorithms to enable "end-to-end communication compression: All communications between machines, including model gradients, forward activations, and backward gradients are compressed into lower precision.This provides up to 4.9X end-to-end speed-up, without sacrificing model quality.

Chengyin Xu, Zenghao Chai, Zhengzhuo Xu et al.

Image retrieval has become an increasingly appealing technique with broad multimedia application prospects, where deep hashing serves as the dominant branch towards low storage and efficient retrieval. In this paper, we carried out in-depth investigations on metric learning in deep hashing for establishing a powerful metric space in multi-label scenarios, where the pair loss suffers high computational overhead and converge difficulty, while the proxy loss is theoretically incapable of expressing the profound label dependencies and exhibits conflicts in the constructed hypersphere space. To address the problems, we propose a novel metric learning framework with Hybrid Proxy-Pair Loss (HyP$^2$ Loss) that constructs an expressive metric space with efficient training complexity w.r.t. the whole dataset. The proposed HyP$^2$ Loss focuses on optimizing the hypersphere space by learnable proxies and excavating data-to-data correlations of irrelevant pairs, which integrates sufficient data correspondence of pair-based methods and high-efficiency of proxy-based methods. Extensive experiments on four standard multi-label benchmarks justify the proposed method outperforms the state-of-the-art, is robust among different hash bits and achieves significant performance gains with a faster, more stable convergence speed. Our code is available at https://github.com/JerryXu0129/HyP2-Loss.

Yuanduo Hong, Jue Wang, Weichao Sun et al.

In the wake of Masked Image Modeling (MIM), a diverse range of plain, non-hierarchical Vision Transformer (ViT) models have been pre-trained with extensive datasets, offering new paradigms and significant potential for semantic segmentation. Current state-of-the-art systems incorporate numerous inductive biases and employ cumbersome decoders. Building upon the original motivations of plain ViTs, which are simplicity and generality, we explore high-performance `minimalist' systems to this end. Our primary purpose is to provide simple and efficient baselines for practical semantic segmentation with plain ViTs. Specifically, we first explore the feasibility and methodology for achieving high-performance semantic segmentation using the last feature map. As a result, we introduce the PlainSeg, a model comprising only three 3$\times$3 convolutions in addition to the transformer layers (either encoder or decoder). In this process, we offer insights into two underlying principles: (i) high-resolution features are crucial to high performance in spite of employing simple up-sampling techniques and (ii) the slim transformer decoder requires a much larger learning rate than the wide transformer decoder. On this basis, we further present the PlainSeg-Hier, which allows for the utilization of hierarchical features. Extensive experiments on four popular benchmarks demonstrate the high performance and efficiency of our methods. They can also serve as powerful tools for assessing the transfer ability of base models in semantic segmentation. Code is available at \url{https://github.com/ydhongHIT/PlainSeg}.

Fei Yin, Yong Zhang, Xiaodong Cun et al.

One-shot talking face generation aims at synthesizing a high-quality talking face video from an arbitrary portrait image, driven by a video or an audio segment. One challenging quality factor is the resolution of the output video: higher resolution conveys more details. In this work, we investigate the latent feature space of a pre-trained StyleGAN and discover some excellent spatial transformation properties. Upon the observation, we explore the possibility of using a pre-trained StyleGAN to break through the resolution limit of training datasets. We propose a novel unified framework based on a pre-trained StyleGAN that enables a set of powerful functionalities, i.e., high-resolution video generation, disentangled control by driving video or audio, and flexible face editing. Our framework elevates the resolution of the synthesized talking face to 1024*1024 for the first time, even though the training dataset has a lower resolution. We design a video-based motion generation module and an audio-based one, which can be plugged into the framework either individually or jointly to drive the video generation. The predicted motion is used to transform the latent features of StyleGAN for visual animation. To compensate for the transformation distortion, we propose a calibration network as well as a domain loss to refine the features. Moreover, our framework allows two types of facial editing, i.e., global editing via GAN inversion and intuitive editing based on 3D morphable models. Comprehensive experiments show superior video quality, flexible controllability, and editability over state-of-the-art methods.

Jue Wang, Wentao Zhu, Pichao Wang et al.

Effective modeling of complex spatiotemporal dependencies in long-form videos remains an open problem. The recently proposed Structured State-Space Sequence (S4) model with its linear complexity offers a promising direction in this space. However, we demonstrate that treating all image-tokens equally as done by S4 model can adversely affect its efficiency and accuracy. To address this limitation, we present a novel Selective S4 (i.e., S5) model that employs a lightweight mask generator to adaptively select informative image tokens resulting in more efficient and accurate modeling of long-term spatiotemporal dependencies in videos. Unlike previous mask-based token reduction methods used in transformers, our S5 model avoids the dense self-attention calculation by making use of the guidance of the momentum-updated S4 model. This enables our model to efficiently discard less informative tokens and adapt to various long-form video understanding tasks more effectively. However, as is the case for most token reduction methods, the informative image tokens could be dropped incorrectly. To improve the robustness and the temporal horizon of our model, we propose a novel long-short masked contrastive learning (LSMCL) approach that enables our model to predict longer temporal context using shorter input videos. We present extensive comparative results using three challenging long-form video understanding datasets (LVU, COIN and Breakfast), demonstrating that our approach consistently outperforms the previous state-of-the-art S4 model by up to 9.6% accuracy while reducing its memory footprint by 23%.

Zhichao Huang, Yanbo Fan, Chen Liu et al.

While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of recent works to accelerate adversarial training is to substitute multi-step attacks (e.g., PGD) with single-step attacks (e.g., FGSM). However, these single-step methods suffer from catastrophic overfitting, where the accuracy against PGD attack suddenly drops to nearly 0% during training, destroying the robustness of the networks. In this work, we study the phenomenon from the perspective of training instances. We show that catastrophic overfitting is instance-dependent and fitting instances with larger gradient norm is more likely to cause catastrophic overfitting. Based on our findings, we propose a simple but effective method, Adversarial Training with Adaptive Step size (ATAS). ATAS learns an instancewise adaptive step size that is inversely proportional to its gradient norm. The theoretical analysis shows that ATAS converges faster than the commonly adopted non-adaptive counterparts. Empirically, ATAS consistently mitigates catastrophic overfitting and achieves higher robust accuracy on CIFAR10, CIFAR100 and ImageNet when evaluated on various adversarial budgets.

Jinbo Xing, Menghan Xia, Yuechen Zhang et al.

Speech-driven 3D facial animation has been widely studied, yet there is still a gap to achieving realism and vividness due to the highly ill-posed nature and scarcity of audio-visual data. Existing works typically formulate the cross-modal mapping into a regression task, which suffers from the regression-to-mean problem leading to over-smoothed facial motions. In this paper, we propose to cast speech-driven facial animation as a code query task in a finite proxy space of the learned codebook, which effectively promotes the vividness of the generated motions by reducing the cross-modal mapping uncertainty. The codebook is learned by self-reconstruction over real facial motions and thus embedded with realistic facial motion priors. Over the discrete motion space, a temporal autoregressive model is employed to sequentially synthesize facial motions from the input speech signal, which guarantees lip-sync as well as plausible facial expressions. We demonstrate that our approach outperforms current state-of-the-art methods both qualitatively and quantitatively. Also, a user study further justifies our superiority in perceptual quality.

Xiaojun Jia, Yong Zhang, Xingxing Wei et al.

Fast adversarial training (FAT) is an efficient method to improve robustness. However, the original FAT suffers from catastrophic overfitting, which dramatically and suddenly reduces robustness after a few training epochs. Although various FAT variants have been proposed to prevent overfitting, they require high training costs. In this paper, we investigate the relationship between adversarial example quality and catastrophic overfitting by comparing the training processes of standard adversarial training and FAT. We find that catastrophic overfitting occurs when the attack success rate of adversarial examples becomes worse. Based on this observation, we propose a positive prior-guided adversarial initialization to prevent overfitting by improving adversarial example quality without extra training costs. This initialization is generated by using high-quality adversarial perturbations from the historical training process. We provide theoretical analysis for the proposed initialization and propose a prior-guided regularization method that boosts the smoothness of the loss function. Additionally, we design a prior-guided ensemble FAT method that averages the different model weights of historical models using different decay rates. Our proposed method, called FGSM-PGK, assembles the prior-guided knowledge, i.e., the prior-guided initialization and model weights, acquired during the historical training process. Evaluations of four datasets demonstrate the superiority of the proposed method.

Yue Chen, Xuan Wang, Xingyu Chen et al.

Neural volume rendering enables photo-realistic renderings of a human performer in free-view, a critical task in immersive VR/AR applications. But the practice is severely limited by high computational costs in the rendering process. To solve this problem, we propose the UV Volumes, a new approach that can render an editable free-view video of a human performer in real-time. It separates the high-frequency (i.e., non-smooth) human appearance from the 3D volume, and encodes them into 2D neural texture stacks (NTS). The smooth UV volumes allow much smaller and shallower neural networks to obtain densities and texture coordinates in 3D while capturing detailed appearance in 2D NTS. For editability, the mapping between the parameterized human model and the smooth texture coordinates allows us a better generalization on novel poses and shapes. Furthermore, the use of NTS enables interesting applications, e.g., retexturing. Extensive experiments on CMU Panoptic, ZJU Mocap, and H36M datasets show that our model can render 960 x 540 images in 30FPS on average with comparable photo-realism to state-of-the-art methods. The project and supplementary materials are available at https://fanegg.github.io/UV-Volumes.

Weiyu Li, Xuelin Chen, Jue Wang et al.

We target a 3D generative model for general natural scenes that are typically unique and intricate. Lacking the necessary volumes of training data, along with the difficulties of having ad hoc designs in presence of varying scene characteristics, renders existing setups intractable. Inspired by classical patch-based image models, we advocate for synthesizing 3D scenes at the patch level, given a single example. At the core of this work lies important algorithmic designs w.r.t the scene representation and generative patch nearest-neighbor module, that address unique challenges arising from lifting classical 2D patch-based framework to 3D generation. These design choices, on a collective level, contribute to a robust, effective, and efficient model that can generate high-quality general natural scenes with both realistic geometric structure and visual appearance, in large quantities and varieties, as demonstrated upon a variety of exemplar scenes.

Maomao Li, Ge Yuan, Cairong Wang et al.

This paper proposes a novel approach to face swapping from the perspective of fine-grained facial editing, dubbed "editing for swapping" (E4S). The traditional face swapping methods rely on global feature extraction and fail to preserve the detailed source identity. In contrast, we propose a Regional GAN Inversion (RGI) method, which allows the explicit disentanglement of shape and texture. Specifically, our E4S performs face swapping in the latent space of a pretrained StyleGAN, where a multi-scale mask-guided encoder is applied to project the texture of each facial component into regional style codes and a mask-guided injection module manipulating feature maps with the style codes. Based on this disentanglement, face swapping can be simplified as style and mask swapping. Besides, due to the large lighting condition gap, transferring the source skin into the target image may lead to disharmony lighting. We propose a re-coloring network to make the swapped face maintain the target lighting condition while preserving the source skin. Further, to deal with the potential mismatch areas during mask exchange, we design a face inpainting module to refine the face shape. The extensive comparisons with state-of-the-art methods demonstrate that our E4S outperforms existing methods in preserving texture, shape, and lighting. Our implementation is available at https://github.com/e4s2024/E4S2024.

Meng Cao, Tianyu Yang, Junwu Weng et al.

Video-Text Pre-training (VTP) aims to learn transferable representations for various downstream tasks from large-scale web videos. To date, almost all existing VTP methods are limited to retrieval-based downstream tasks, e.g., video retrieval, whereas their transfer potentials on localization-based tasks, e.g., temporal grounding, are under-explored. In this paper, we experimentally analyze and demonstrate the incompatibility of current VTP methods with localization tasks, and propose a novel Localization-oriented Video-Text Pre-training framework, dubbed as LocVTP. Specifically, we perform the fine-grained contrastive alignment as a complement to the coarse-grained one by a clip-word correspondence discovery scheme. To further enhance the temporal reasoning ability of the learned feature, we propose a context projection head and a temporal aware contrastive loss to perceive the contextual relationships. Extensive experiments on four downstream tasks across six datasets demonstrate that our LocVTP achieves state-of-the-art performance on both retrieval-based and localization-based tasks. Furthermore, we conduct comprehensive ablation studies and thorough analyses to explore the optimum model designs and training strategies.

Zhian Liu, Maomao Li, Yong Zhang et al.

We present a novel paradigm for high-fidelity face swapping that faithfully preserves the desired subtle geometry and texture details. We rethink face swapping from the perspective of fine-grained face editing, \textit{i.e., ``editing for swapping'' (E4S)}, and propose a framework that is based on the explicit disentanglement of the shape and texture of facial components. Following the E4S principle, our framework enables both global and local swapping of facial features, as well as controlling the amount of partial swapping specified by the user. Furthermore, the E4S paradigm is inherently capable of handling facial occlusions by means of facial masks. At the core of our system lies a novel Regional GAN Inversion (RGI) method, which allows the explicit disentanglement of shape and texture. It also allows face swapping to be performed in the latent space of StyleGAN. Specifically, we design a multi-scale mask-guided encoder to project the texture of each facial component into regional style codes. We also design a mask-guided injection module to manipulate the feature maps with the style codes. Based on the disentanglement, face swapping is reformulated as a simplified problem of style and mask swapping. Extensive experiments and comparisons with current state-of-the-art methods demonstrate the superiority of our approach in preserving texture and shape details, as well as working with high resolution images. The project page is http://e4s2022.github.io

Jingxiang Sun, Xuan Wang, Yichun Shi et al.

Existing 3D-aware facial generation methods face a dilemma in quality versus editability: they either generate editable results in low resolution or high-quality ones with no editing flexibility. In this work, we propose a new approach that brings the best of both worlds together. Our system consists of three major components: (1) a 3D-semantics-aware generative model that produces view-consistent, disentangled face images and semantic masks; (2) a hybrid GAN inversion approach that initialize the latent codes from the semantic and texture encoder, and further optimized them for faithful reconstruction; and (3) a canonical editor that enables efficient manipulation of semantic masks in canonical view and product high-quality editing results. Our approach is competent for many applications, e.g. free-view face drawing, editing, and style control. Both quantitative and qualitative results show that our method reaches the state-of-the-art in terms of photorealism, faithfulness, and efficiency.

Li Ma, Xiaoyu Li, Jing Liao et al.

Implicit radiance functions emerged as a powerful scene representation for reconstructing and rendering photo-realistic views of a 3D scene. These representations, however, suffer from poor editability. On the other hand, explicit representations such as polygonal meshes allow easy editing but are not as suitable for reconstructing accurate details in dynamic human heads, such as fine facial features, hair, teeth, and eyes. In this work, we present Neural Parameterization (NeP), a hybrid representation that provides the advantages of both implicit and explicit methods. NeP is capable of photo-realistic rendering while allowing fine-grained editing of the scene geometry and appearance. We first disentangle the geometry and appearance by parameterizing the 3D geometry into 2D texture space. We enable geometric editability by introducing an explicit linear deformation blending layer. The deformation is controlled by a set of sparse key points, which can be explicitly and intuitively displaced to edit the geometry. For appearance, we develop a hybrid 2D texture consisting of an explicit texture map for easy editing and implicit view and time-dependent residuals to model temporal and view variations. We compare our method to several reconstruction and editing baselines. The results show that the NeP achieves almost the same level of rendering accuracy while maintaining high editability.

Jiancong Xiao, Zeyu Qin, Yanbo Fan et al.

Adversarial Training (AT) has been demonstrated as one of the most effective methods against adversarial examples. While most existing works focus on AT with a single type of perturbation e.g., the $\ell_\infty$ attacks), DNNs are facing threats from different types of adversarial examples. Therefore, adversarial training for multiple perturbations (ATMP) is proposed to generalize the adversarial robustness over different perturbation types (in $\ell_1$, $\ell_2$, and $\ell_\infty$ norm-bounded perturbations). However, the resulting model exhibits trade-off between different attacks. Meanwhile, there is no theoretical analysis of ATMP, limiting its further development. In this paper, we first provide the smoothness analysis of ATMP and show that $\ell_1$, $\ell_2$, and $\ell_\infty$ adversaries give different contributions to the smoothness of the loss function of ATMP. Based on this, we develop the stability-based excess risk bounds and propose adaptive smoothness-weighted adversarial training for multiple perturbations. Theoretically, our algorithm yields better bounds. Empirically, our experiments on CIFAR10 and CIFAR100 achieve the state-of-the-art performance against the mixture of multiple perturbations attacks.

Tianshuo Yuan, Yuxiang Lin, Jue Wang et al.

Combining Vision Large Language Models (VLLMs) with diffusion models offers a powerful method for executing image editing tasks based on human language instructions. However, language instructions alone often fall short in accurately conveying user requirements, particularly when users want to add, replace elements in specific areas of an image. Luckily, masks can effectively indicate the exact locations or elements to be edited, while they require users to precisely draw the shapes at the desired locations, which is highly user-unfriendly. To address this, we propose FlexEdit, an end-to-end image editing method that leverages both free-shape masks and language instructions for Flexible Editing. Our approach employs a VLLM in comprehending the image content, mask, and user instructions. Additionally, we introduce the Mask Enhance Adapter (MEA) that fuses the embeddings of the VLLM with the image data, ensuring a seamless integration of mask information and model output embeddings. Furthermore, we construct FSMI-Edit, a benchmark specifically tailored for free-shape mask, including 8 types of free-shape mask. Extensive experiments show that our method achieves state-of-the-art (SOTA) performance in LLM-based image editing, and our simple prompting technique stands out in its effectiveness. The code and data can be found at https://github.com/A-new-b/flex_edit.

Jiancong Xiao, Yanbo Fan, Ruoyu Sun et al.

In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalization ability on the test set. This phenomenon is called robust overfitting, and it can be observed when adversarially training neural nets on common datasets, including SVHN, CIFAR-10, CIFAR-100, and ImageNet. In this paper, we study the robust overfitting issue of adversarial training by using tools from uniform stability. One major challenge is that the outer function (as a maximization of the inner function) is nonsmooth, so the standard technique (e.g., hardt et al., 2016) cannot be applied. Our approach is to consider $η$-approximate smoothness: we show that the outer function satisfies this modified smoothness assumption with $η$ being a constant related to the adversarial perturbation $ε$. Based on this, we derive stability-based generalization bounds for stochastic gradient descent (SGD) on the general class of $η$-approximate smooth functions, which covers the adversarial loss. Our results suggest that robust test accuracy decreases in $ε$ when $T$ is large, with a speed between $Ω(ε\sqrt{T})$ and $\mathcal{O}(εT)$. This phenomenon is also observed in practice. Additionally, we show that a few popular techniques for adversarial training (e.g., early stopping, cyclic learning rate, and stochastic weight averaging) are stability-promoting in theory.

Fang Zhao, Zekun Li, Shaoli Huang et al.

This paper proposes an anchor-based deformation model, namely AnchorDEF, to predict 3D garment animation from a body motion sequence. It deforms a garment mesh template by a mixture of rigid transformations with extra nonlinear displacements. A set of anchors around the mesh surface is introduced to guide the learning of rigid transformation matrices. Once the anchor transformations are found, per-vertex nonlinear displacements of the garment template can be regressed in a canonical space, which reduces the complexity of deformation space learning. By explicitly constraining the transformed anchors to satisfy the consistencies of position, normal and direction, the physical meaning of learned anchor transformations in space is guaranteed for better generalization. Furthermore, an adaptive anchor updating is proposed to optimize the anchor position by being aware of local mesh topology for learning representative anchor transformations. Qualitative and quantitative experiments on different types of garments demonstrate that AnchorDEF achieves the state-of-the-art performance on 3D garment deformation prediction in motion, especially for loose-fitting garments.

Mingdeng Cao, Zhihang Zhong, Yanbo Fan et al.

This paper aims at exploring how to synthesize close-to-real blurs that existing video deblurring models trained on them can generalize well to real-world blurry videos. In recent years, deep learning-based approaches have achieved promising success on video deblurring task. However, the models trained on existing synthetic datasets still suffer from generalization problems over real-world blurry scenarios with undesired artifacts. The factors accounting for the failure remain unknown. Therefore, we revisit the classical blur synthesis pipeline and figure out the possible reasons, including shooting parameters, blur formation space, and image signal processor~(ISP). To analyze the effects of these potential factors, we first collect an ultra-high frame-rate (940 FPS) RAW video dataset as the data basis to synthesize various kinds of blurs. Then we propose a novel realistic blur synthesis pipeline termed as RAW-Blur by leveraging blur formation cues. Through numerous experiments, we demonstrate that synthesizing blurs in the RAW space and adopting the same ISP as the real-world testing data can effectively eliminate the negative effects of synthetic data. Furthermore, the shooting parameters of the synthesized blurry video, e.g., exposure time and frame-rate play significant roles in improving the performance of deblurring models. Impressively, the models trained on the blurry data synthesized by the proposed RAW-Blur pipeline can obtain more than 5dB PSNR gain against those trained on the existing synthetic blur datasets. We believe the novel realistic synthesis pipeline and the corresponding RAW video dataset can help the community to easily construct customized blur datasets to improve real-world video deblurring performance largely, instead of laboriously collecting real data pairs.

Jiancong Xiao, Liusha Yang, Yanbo Fan et al.

Deep neural networks (DNNs) are shown to be vulnerable to adversarial examples. A well-trained model can be easily attacked by adding small perturbations to the original data. One of the hypotheses of the existence of the adversarial examples is the off-manifold assumption: adversarial examples lie off the data manifold. However, recent research showed that on-manifold adversarial examples also exist. In this paper, we revisit the off-manifold assumption and want to study a question: at what level is the poor performance of neural networks against adversarial attacks due to on-manifold adversarial examples? Since the true data manifold is unknown in practice, we consider two approximated on-manifold adversarial examples on both real and synthesis datasets. On real datasets, we show that on-manifold adversarial examples have greater attack rates than off-manifold adversarial examples on both standard-trained and adversarially-trained models. On synthetic datasets, theoretically, We prove that on-manifold adversarial examples are powerful, yet adversarial training focuses on off-manifold directions and ignores the on-manifold adversarial examples. Furthermore, we provide analysis to show that the properties derived theoretically can also be observed in practice. Our analysis suggests that on-manifold adversarial examples are important, and we should pay more attention to on-manifold adversarial examples for training robust models.

David Fan, Jue Wang, Shuai Liao et al. · amazon-science

Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient regions. However, the robustness of such visual cues depends on how often input videos match underlying assumptions. On the other hand, natural language description is an information dense representation of video that implicitly captures saliency without requiring modality-specific assumptions, and has not been explored yet for video MAE. To this end, we introduce a novel text-guided masking algorithm (TGM) that masks the video regions with highest correspondence to paired captions. Without leveraging any explicit visual cues for saliency, our TGM is competitive with state-of-the-art masking algorithms such as motion-guided masking. To further benefit from the semantics of natural language for masked reconstruction, we next introduce a unified framework for joint MAE and masked video-text contrastive learning. We show that across existing masking algorithms, unifying MAE and masked video-text contrastive learning improves downstream performance compared to pure MAE on a variety of video recognition tasks, especially for linear probe. Within this unified framework, our TGM achieves the best relative performance on five action recognition and one egocentric datasets, highlighting the complementary nature of natural language for masked video modeling.

Zixiao Wang, Junwu Weng, Chun Yuan et al.

Learning with noisy label (LNL) is a classic problem that has been extensively studied for image tasks, but much less for video in the literature. A straightforward migration from images to videos without considering the properties of videos, such as computational cost and redundant information, is not a sound choice. In this paper, we propose two new strategies for video analysis with noisy labels: 1) A lightweight channel selection method dubbed as Channel Truncation for feature-based label noise detection. This method selects the most discriminative channels to split clean and noisy instances in each category; 2) A novel contrastive strategy dubbed as Noise Contrastive Learning, which constructs the relationship between clean and noisy instances to regularize model training. Experiments on three well-known benchmark datasets for video classification show that our proposed tru{\bf N}cat{\bf E}-split-contr{\bf A}s{\bf T} (NEAT) significantly outperforms the existing baselines. By reducing the dimension to 10\% of it, our method achieves over 0.4 noise detection F1-score and 5\% classification accuracy improvement on Mini-Kinetics dataset under severe noise (symmetric-80\%). Thanks to Noise Contrastive Learning, the average classification accuracy improvement on Mini-Kinetics and Sth-Sth-V1 is over 1.6\%.

Jia Liu, Changlin Li, Qirui Sun et al.

Fine-tuning advanced diffusion models for high-quality image stylization usually requires large training datasets and substantial computational resources, hindering their practical applicability. We propose Ada-Adapter, a novel framework for few-shot style personalization of diffusion models. Ada-Adapter leverages off-the-shelf diffusion models and pre-trained image feature encoders to learn a compact style representation from a limited set of source images. Our method enables efficient zero-shot style transfer utilizing a single reference image. Furthermore, with a small number of source images (three to five are sufficient) and a few minutes of fine-tuning, our method can capture intricate style details and conceptual characteristics, generating high-fidelity stylized images that align well with the provided text prompts. We demonstrate the effectiveness of our approach on various artistic styles, including flat art, 3D rendering, and logo design. Our experimental results show that Ada-Adapter outperforms existing zero-shot and few-shot stylization methods in terms of output quality, diversity, and training efficiency.

Yunpeng Bai, Cairong Wang, Chun Yuan et al.

Existing neural style transfer researches have studied to match statistical information between the deep features of content and style images, which were extracted by a pre-trained VGG, and achieved significant improvement in synthesizing artistic images. However, in some cases, the feature statistics from the pre-trained encoder may not be consistent with the visual style we perceived. For example, the style distance between images of different styles is less than that of the same style. In such an inappropriate latent space, the objective function of the existing methods will be optimized in the wrong direction, resulting in bad stylization results. In addition, the lack of content details in the features extracted by the pre-trained encoder also leads to the content leak problem. In order to solve these issues in the latent space used by style transfer, we propose two contrastive training schemes to get a refined encoder that is more suitable for this task. The style contrastive loss pulls the stylized result closer to the same visual style image and pushes it away from the content image. The content contrastive loss enables the encoder to retain more available details. We can directly add our training scheme to some existing style transfer methods and significantly improve their results. Extensive experimental results demonstrate the effectiveness and superiority of our methods.

Jue Wang, Yuxiang Lin, Qi Zhao et al.

The widespread use of various chemical gases in industrial processes necessitates effective measures to prevent their leakage during transportation and storage, given their high toxicity. Thermal infrared-based computer vision detection techniques provide a straightforward approach to identify gas leakage areas. However, the development of high-quality algorithms has been challenging due to the low texture in thermal images and the lack of open-source datasets. In this paper, we present the RGB-Thermal Cross Attention Network (RT-CAN), which employs an RGB-assisted two-stream network architecture to integrate texture information from RGB images and gas area information from thermal images. Additionally, to facilitate the research of invisible gas detection, we introduce Gas-DB, an extensive open-source gas detection database including about 1.3K well-annotated RGB-thermal images with eight variant collection scenes. Experimental results demonstrate that our method successfully leverages the advantages of both modalities, achieving state-of-the-art (SOTA) performance among RGB-thermal methods, surpassing single-stream SOTA models in terms of accuracy, Intersection of Union (IoU), and F2 metrics by 4.86%, 5.65%, and 4.88%, respectively. The code and data can be found at https://github.com/logic112358/RT-CAN.

Xiaolong Wang, Zhi-Qi Cheng, Jue Wang et al.

Fashion image editing is a crucial tool for designers to convey their creative ideas by visualizing design concepts interactively. Current fashion image editing techniques, though advanced with multimodal prompts and powerful diffusion models, often struggle to accurately identify editing regions and preserve the desired garment texture detail. To address these challenges, we introduce a new multimodal fashion image editing architecture based on latent diffusion models, called Detail-Preserved Diffusion Models (DPDEdit). DPDEdit guides the fashion image generation of diffusion models by integrating text prompts, region masks, human pose images, and garment texture images. To precisely locate the editing region, we first introduce Grounded-SAM to predict the editing region based on the user's textual description, and then combine it with other conditions to perform local editing. To transfer the detail of the given garment texture into the target fashion image, we propose a texture injection and refinement mechanism. Specifically, this mechanism employs a decoupled cross-attention layer to integrate textual descriptions and texture images, and incorporates an auxiliary U-Net to preserve the high-frequency details of generated garment texture. Additionally, we extend the VITON-HD dataset using a multimodal large language model to generate paired samples with texture images and textual descriptions. Extensive experiments show that our DPDEdit outperforms state-of-the-art methods in terms of image fidelity and coherence with the given multimodal inputs.

Boyu Zhang, Hongliang Yuan, Mingyan Zhu et al.

Generating high-quality, realistic rendering images for real-time applications generally requires tracing a few samples-per-pixel (spp) and using deep learning-based approaches to denoise the resulting low-spp images. Existing denoising methods have yet to achieve real-time performance at high resolutions due to the physically-based sampling and network inference time costs. In this paper, we propose a novel Monte Carlo sampling strategy to accelerate the sampling process and a corresponding denoiser, subpixel sampling reconstruction (SSR), to obtain high-quality images. Extensive experiments demonstrate that our method significantly outperforms previous approaches in denoising quality and reduces overall time costs, enabling real-time rendering capabilities at 2K resolution.

Youwei Liang, Chongjian Ge, Zhan Tong et al.

Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Complete leverage of these image tokens brings redundant computations since not all the tokens are attentive in MHSA. Examples include that tokens containing semantically meaningless or distractive image backgrounds do not positively contribute to the ViT predictions. In this work, we propose to reorganize image tokens during the feed-forward process of ViT models, which is integrated into ViT during training. For each forward inference, we identify the attentive image tokens between MHSA and FFN (i.e., feed-forward network) modules, which is guided by the corresponding class token attention. Then, we reorganize image tokens by preserving attentive image tokens and fusing inattentive ones to expedite subsequent MHSA and FFN computations. To this end, our method EViT improves ViTs from two perspectives. First, under the same amount of input image tokens, our method reduces MHSA and FFN computation for efficient inference. For instance, the inference speed of DeiT-S is increased by 50% while its recognition accuracy is decreased by only 0.3% for ImageNet classification. Second, by maintaining the same computational cost, our method empowers ViTs to take more image tokens as input for recognition accuracy improvement, where the image tokens are from higher resolution images. An example is that we improve the recognition accuracy of DeiT-S by 1% for ImageNet classification at the same computational cost of a vanilla DeiT-S. Meanwhile, our method does not introduce more parameters to ViTs. Experiments on the standard benchmarks show the effectiveness of our method. The code is available at https://github.com/youweiliang/evit

Haipeng Li, Shuaicheng Liu, Jue Wang

Mobile captured images can be aligned using their gyroscope sensors. Optical image stabilizer (OIS) terminates this possibility by adjusting the images during the capturing. In this work, we propose a deep network that compensates the motions caused by the OIS, such that the gyroscopes can be used for image alignment on the OIS cameras. To achieve this, first, we record both videos and gyroscopes with an OIS camera as training data. Then, we convert gyroscope readings into motion fields. Second, we propose a Fundamental Mixtures motion model for rolling shutter cameras, where an array of rotations within a frame are extracted as the ground-truth guidance. Third, we train a convolutional neural network with gyroscope motions as input to compensate for the OIS motion. Once finished, the compensation network can be applied for other scenes, where the image alignment is purely based on gyroscopes with no need for images contents, delivering strong robustness. Experiments show that our results are comparable with that of non-OIS cameras, and outperform image-based alignment results with a relatively large margin. Code and dataset are available at https://github.com/lhaippp/DeepOIS

Jiaming Liu, Chi-Hao Wu, Yuzhi Wang et al.

In this paper, we present new data pre-processing and augmentation techniques for DNN-based raw image denoising. Compared with traditional RGB image denoising, performing this task on direct camera sensor readings presents new challenges such as how to effectively handle various Bayer patterns from different data sources, and subsequently how to perform valid data augmentation with raw images. To address the first problem, we propose a Bayer pattern unification (BayerUnify) method to unify different Bayer patterns. This allows us to fully utilize a heterogeneous dataset to train a single denoising model instead of training one model for each pattern. Furthermore, while it is essential to augment the dataset to improve model generalization and performance, we discovered that it is error-prone to modify raw images by adapting augmentation methods designed for RGB images. Towards this end, we present a Bayer preserving augmentation (BayerAug) method as an effective approach for raw image augmentation. Combining these data processing technqiues with a modified U-Net, our method achieves a PSNR of 52.11 and a SSIM of 0.9969 in NTIRE 2019 Real Image Denoising Challenge, demonstrating the state-of-the-art performance. Our code is available at https://github.com/Jiaming-Liu/BayerUnifyAug.

Yuqian Zhou, Jianbo Jiao, Haibin Huang et al.

Discriminative learning-based image denoisers have achieved promising performance on synthetic noises such as Additive White Gaussian Noise (AWGN). The synthetic noises adopted in most previous work are pixel-independent, but real noises are mostly spatially/channel-correlated and spatially/channel-variant. This domain gap yields unsatisfied performance on images with real noises if the model is only trained with AWGN. In this paper, we propose a novel approach to boost the performance of a real image denoiser which is trained only with synthetic pixel-independent noise data dominated by AWGN. First, we train a deep model that consists of a noise estimator and a denoiser with mixed AWGN and Random Value Impulse Noise (RVIN). We then investigate Pixel-shuffle Down-sampling (PD) strategy to adapt the trained model to real noises. Extensive experiments demonstrate the effectiveness and generalization of the proposed approach. Notably, our method achieves state-of-the-art performance on real sRGB images in the DND benchmark among models trained with synthetic noises. Codes are available at https://github.com/yzhouas/PD-Denoising-pytorch.

Zhenzhou Jin, Li You, Jue Wang et al.

Channel knowledge map (CKM) has received widespread attention as an emerging enabling technology for environment-aware wireless communications. It involves the construction of databases containing location-specific channel knowledge, which are then leveraged to facilitate channel state information (CSI) acquisition and transceiver design. In this context, a fundamental challenge lies in efficiently constructing the CKM based on a given wireless propagation environment. Most existing methods are based on stochastic modeling and sequence prediction, which do not fully exploit the inherent physical characteristics of the propagation environment, resulting in low accuracy and high computational complexity. To address these limitations, we propose a Laplacian pyramid (LP)-based CKM construction scheme to predict the channel knowledge at arbitrary locations in a targeted area. Specifically, we first view the channel knowledge as a 2-D image and transform the CKM construction problem into an image-to-image (I2I) inpainting task, which predicts the channel knowledge at a specific location by recovering the corresponding pixel value in the image matrix. Then, inspired by the reversible and closed-form structure of the LP, we show its natural suitability for our task in designing a fast I2I mapping network. For different frequency components of LP decomposition, we design tailored networks accordingly. Besides, to encode the global structural information of the propagation environment, we introduce self-attention and cross-covariance attention mechanisms in different layers, respectively. Finally, experimental results show that the proposed scheme outperforms the benchmark, achieving higher reconstruction accuracy while with lower computational complexity. Moreover, the proposed approach has a strong generalization ability and can be implemented in different wireless communication scenarios.

Yinhe Liu, Sunan Shi, Zhuo Zheng et al.

Semantic Change Detection (SCD) is recognized as both a crucial and challenging task in the field of image analysis. Traditional methods for SCD have predominantly relied on the comparison of image pairs. However, this approach is significantly hindered by substantial imaging differences, which arise due to variations in shooting times, atmospheric conditions, and angles. Such discrepancies lead to two primary issues: the under-detection of minor yet significant changes, and the generation of false alarms due to temporal variances. These factors often result in unchanged objects appearing markedly different in multi-temporal images. In response to these challenges, the MapChange framework has been developed. This framework introduces a novel paradigm that synergizes temporal-invariant historical map data with contemporary high-resolution images. By employing this combination, the temporal variance inherent in conventional image pair comparisons is effectively mitigated. The efficacy of the MapChange framework has been empirically validated through comprehensive testing on two public datasets. These tests have demonstrated the framework's marked superiority over existing state-of-the-art SCD methods.

Jun Zhang, Jue Wang, Huan Li et al.

We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The drafting stage generates draft tokens at a slightly lower quality but more quickly, which is achieved by selectively skipping certain intermediate layers during drafting. Subsequently, the verification stage employs the original LLM to validate those draft output tokens in one forward pass. This process ensures the final output remains identical to that produced by the unaltered LLM. Moreover, the proposed method requires no additional neural network training and no extra memory footprint, making it a plug-and-play and cost-effective solution for inference acceleration. Benchmarks with LLaMA-2 and its variants demonstrated a speedup up to 1.99$\times$.

Jue Wang, Lorenzo Torresani

Video transformers have recently emerged as an effective alternative to convolutional networks for action classification. However, most prior video transformers adopt either global space-time attention or hand-defined strategies to compare patches within and across frames. These fixed attention schemes not only have high computational cost but, by comparing patches at predetermined locations, they neglect the motion dynamics in the video. In this paper, we introduce the Deformable Video Transformer (DVT), which dynamically predicts a small subset of video patches to attend for each query location based on motion information, thus allowing the model to decide where to look in the video based on correspondences across frames. Crucially, these motion-based correspondences are obtained at zero-cost from information stored in the compressed format of the video. Our deformable attention mechanism is optimised directly with respect to classification performance, thus eliminating the need for suboptimal hand-design of attention strategies. Experiments on four large-scale video benchmarks (Kinetics-400, Something-Something-V2, EPIC-KITCHENS and Diving-48) demonstrate that, compared to existing video transformers, our model achieves higher accuracy at the same or lower computational cost, and it attains state-of-the-art results on these four datasets.

Kai Ye, Siyan Dong, Qingnan Fan et al.

We study the problem of multi-robot active mapping, which aims for complete scene map construction in minimum time steps. The key to this problem lies in the goal position estimation to enable more efficient robot movements. Previous approaches either choose the frontier as the goal position via a myopic solution that hinders the time efficiency, or maximize the long-term value via reinforcement learning to directly regress the goal position, but does not guarantee the complete map construction. In this paper, we propose a novel algorithm, namely NeuralCoMapping, which takes advantage of both approaches. We reduce the problem to bipartite graph matching, which establishes the node correspondences between two graphs, denoting robots and frontiers. We introduce a multiplex graph neural network (mGNN) that learns the neural distance to fill the affinity matrix for more effective graph matching. We optimize the mGNN with a differentiable linear assignment layer by maximizing the long-term values that favor time efficiency and map completeness via reinforcement learning. We compare our algorithm with several state-of-the-art multi-robot active mapping approaches and adapted reinforcement-learning baselines. Experimental results demonstrate the superior performance and exceptional generalization ability of our algorithm on various indoor scenes and unseen number of robots, when only trained with 9 indoor scenes.