论文检索

Chenyu Mu, Jiahua Li, Kun Wei, Cheng Deng

Temporal Action Localization (TAL) aims to accurately identify the start and end times of actions in untrimmed videos and classify them according to specific labels. However, the complexity and imbalance between target actions and background in video data make this task particularly challenging. Although relying on large amounts of finely annotated data has led to some progress in existing methods, the presence of noisy labels in large-scale annotations limits their application in open-world scenarios. To address this issue, we take the perspective of the data itself, modeling the different energy patterns exhibited by the action foreground and background in video data to enhance video content inference. Specifically, we propose the Energy-Driven Meta Purifier (EDMP) method, which utilizes a meta-learning training paradigm to avoid dependence on extensive and precise manual annotations. Under this pipeline, we use energy modeling to distinguish between different actions and backgrounds from the perspective of energy differences, thereby improving the model's robustness to category noise. Additionally, these energy-based distinctions are employed to further refine action boundaries, enhancing the model's robustness to boundary noise. Experiments on THUMOS14 and ActivityNet1.3 datasets show that EDMP effectively enhances the robustness of TAL models.

Keith G. Mills, Mohammad Salameh, Ruichen Chen, Negar Hassanpour, Wei Lu, Di Niu

Diffusion Models (DM) have democratized AI image generation through an iterative denoising process. Quantization is a major technique to alleviate the inference cost and reduce the size of DM denoiser networks. However, as denoisers evolve from variants of convolutional U-Nets toward newer Transformer architectures, it is of growing importance to understand the quantization sensitivity of different weight layers, operations and architecture types to performance. In this work, we address this challenge with Qua2SeDiMo, a mixed-precision Post-Training Quantization framework that generates explainable insights on the cost-effectiveness of various model weight quantization methods for different denoiser operation types and block structures. We leverage these insights to make high-quality mixed-precision quantization decisions for a myriad of diffusion models ranging from foundational U-Nets to state-of-the-art Transformers. As a result, Qua2SeDiMo can construct 3.4-bit, 3.9-bit, 3.65-bit and 3.7-bit weight quantization on PixArt-α, PixArt-Σ, Hunyuan-DiT and SDXL, respectively. We further pair our weight-quantization configurations with 6-bit activation quantization and outperform existing approaches in terms of quantitative metrics and generative image quality.

Honglei Miao, Fan Ma, Ruijie Quan, Kun Zhan, Yi Yang

Human motion generative models have enabled promising applications, but the ability of text-to-motion (T2M) models to produce realistic motions raises security concerns if exploited maliciously. Despite growing interest in T2M, limited research focus on safeguarding these models against adversarial attacks, with existing work on text-to-image models proving insufficient for the unique motion domain. In the paper, we propose ALERT-Motion, an autonomous framework that leverages large language models (LLMs) to generate targeted adversarial attacks against black-box T2M models. Unlike prior methods that modify prompts through predefined rules, ALERT-Motion uses the knowledge of LLMs of human motion to autonomously generate subtle yet powerful adversarial text descriptions. It comprises two key modules: an adaptive dispatching module that constructs an LLM-based agent to iteratively refine and search for adversarial prompts; and a multimodal information contrastive module that extracts semantically relevant motion information to guide the agent's search. Through this LLM-driven approach, ALERT-Motion produces adversarial prompts querying victim models to produce outputs closely matching targeted motions, while avoiding obvious perturbations. Evaluations across popular T2M models demonstrate ALERT-Motion's superiority over previous methods, achieving higher attack success rates with stealthier adversarial prompts. This pioneering work on T2M adversarial attacks highlights the urgency of developing defensive measures as motion generation technology advances, urging further research into safe and responsible deployment.

Yucong Meng, Zhiwei Yang, Yonghong Shi, Zhijian Song

The accelerated MRI reconstruction process presents a challenging ill-posed inverse problem due to the extensive under-sampling in k-space. Recently, Vision Transformers (ViTs) have become the mainstream for this task, demonstrating substantial performance improvements. However, there are still three significant issues remain unaddressed: (1) ViTs struggle to capture high-frequency components of images, limiting their ability to detect local textures and edge information, thereby impeding MRI restoration; (2) Previous methods calculate multi-head self-attention (MSA) among both related and unrelated tokens in content, introducing noise and significantly increasing computational burden; (3) The naive feed-forward network in ViTs cannot model the multi-scale information that is important for image restoration. In this paper, we propose FPS-Former, a powerful ViT-based framework, to address these issues from the perspectives of frequency modulation, spatial purification, and scale diversification. Specifically, for issue (1), we introduce a frequency modulation attention module to enhance the self-attention map by adaptively re-calibrating the frequency information in a Laplacian pyramid. For issue (2), we customize a spatial purification attention module to capture interactions among closely related tokens, thereby reducing redundant or irrelevant feature representations. For issue (3), we propose an efficient feed-forward network based on a hybrid-scale fusion strategy. Comprehensive experiments conducted on three public datasets show that our FPS-Former outperforms state-of-the-art methods while requiring lower computational costs.

GuangHao Meng, Sunan He, Jinpeng Wang, Tao Dai, Letian Zhang, Jieming Zhu, Qing Li, Gang Wang, Rui Zhang, Yong Jiang

Vision-language retrieval (VLR) has attracted significant attention in both academia and industry, which involves using text (or images) as queries to retrieve corresponding images (or text). However, existing methods often neglect the rich visual semantics knowledge of entities, thus leading to incorrect retrieval results. To address this problem, we propose the Entity Visual Description enhanced CLIP (EvdCLIP), designed to leverage the visual knowledge of entities to enrich queries. Specifically, since humans recognize entities through visual cues, we employ a large language model (LLM) to generate Entity Visual Descriptions (EVDs) as alignment cues to complement textual data. These EVDs are then integrated into raw queries to create visually-rich, EVD-enhanced queries. Furthermore, recognizing that EVD-enhanced queries may introduce noise or low-quality expansions, we develop a novel, trainable EVD-aware Rewriter (EaRW) for vision-language retrieval tasks. EaRW utilizes EVD knowledge and the generative capabilities of the language model to effectively rewrite queries. With our specialized training strategy, EaRW can generate high-quality and low-noise EVD-enhanced queries. Extensive quantitative and qualitative experiments on image-text retrieval benchmarks validate the superiority of EvdCLIP on vision-language retrieval tasks.

Ge Meng, Jingjia Huang, Jingyan Tu, Yingying Wang, Yunlong Lin, Xiaotong Tu, Yue Huang, Xinghao Ding

Pan-sharpening aims to preserve the spectral information of the multi-spectral (MS) image while leveraging the high-frequency details from the guided high-resolution panchromatic (PAN) image to enhance its spatial resolution. The key challenge is how to preserve the spectral information from the MS image and the spatial details from the PAN image as much as possible. Diffusion models have achieved favorable results in image restoration and synthesis tasks but suffer from excessive computational resource and time consumption. In this paper, we design a novel and computationally efficient diffusion-based pan-sharpening network that achieves accelerated diffusion while reducing task complexity by decoupling the high and low-frequency components of the fused image. Specifically, leveraging the information-preserving characteristic of the wavelet transformation, we introduce a Wavelet-based Low-frequency Diffusion Model (WLDM). WLDM generates the low-frequency coefficient of high-resolution MS (HRMS) image from the low-resolution MS (LRMS) image. This approach significantly reduces computational resources and complexity compared to the direct restoration of the HRMS image. Furthermore, we have devised a High-frequency Information Restoration Module (HIRM) to restore the high-frequency information in the HRMS image through the interaction of high-frequency coefficients from the PAN image in three directions. Extensive experiments on three different datasets demonstrate that our method outperforms existing approaches in both quantitative metrics, qualitative metrics, and inference efficiency.

Ge Meng, Jingyan Tu, Jingjia Huang, Yunlong Lin, Yingying Wang, Xiaotong Tu, Yue Huang, Xinghao Ding

Hyperspectral image (HSI) reconstruction aims to restore the original 3D HSIs from the 2D hyperspectral snapshot compressive images (SCIs). The key to high-fidelity HSI reconstruction lies in designing refined spatial and spectral attention mechanisms, which are crucial for generating fine-grained representations of HSI based on the limited spatial and spectral information available in SCI. Recently, Mamba has demonstrated remarkable performance and efficiency in modeling spatial correlations. Its implicit attention mechanism generates three orders of magnitude more attention matrices than transformers, significantly raising the performance ceiling for HSI reconstruction. In this paper, we propose a novel joint SSM network named Sp3ctralMamba for HSI reconstruction. Sp3ctralMamba integrates frequency domain knowledge and physical priors to enhance reconstruction quality. Specifically, we first perform hierarchical decomposition of the 3D HSI embedding to mitigate the negative impact of distant bands on reconstruction. Next, we design a joint SSM block S3Mamba (S3MAB) to perform parallel scans of the embeddings from different bands. In addition to the conventional vanilla scan, S3MAB introduces a local scanning scheme to address the reconstruction challenges posed by the spatial sparsity of spectral information. Furthermore, a spiral scanning scheme in the frequency domain is incorporated to enhance the order correlation between different frequency signals. Finally, we introduce energy priors and structural priors to constrain the generation of spectral and spatial representations during the training process. Extensive experiments on both simulated and real datasets demonstrate that Sp3ctralMamba significantly elevates HSI reconstruction performance to a new level, surpassing SOTA methods in both quantitative and qualitative metrics.

Fan'an Meng, Chaoran Cui, Hongjun Dai, Shuai Gong

Test-time prompt tuning (TPT) aims to adjust the vision-language models (e.g., CLIP) with learnable prompts during the inference phase. However, previous works overlooked that pre-trained models as a service (MaaS) have become a noticeable trend due to their commercial usage and potential risk of misuse. In the context of MaaS, users can only design prompts in inputs and query the black-box vision-language models through inference APIs, rendering the previous paradigm of utilizing gradient for prompt tuning is infeasible. In this paper, we propose black-box test-time prompt tuning (B²TPT), a novel framework that addresses the challenge of optimizing prompts without gradients in an unsupervised manner. Specifically, B²TPT designs a consistent or confident (CoC) pseudo-labeling strategy to generate high-quality pseudo-labels from the outputs. Subsequently, we propose to optimize low-dimensional intrinsic prompts using a derivative-free evolution algorithm and to project them onto the original text and vision prompts. This strategy addresses the gradient-free challenge while reducing complexity. Extensive experiments across 15 datasets demonstrate the superiority of B²TPT. The results show that B²TPT not only outperforms CLIP's zero-shot inference at test time, but also surpasses other gradient-based TPT methods.

Chutian Meng, Fan Ma, Jiaxu Miao, Chi Zhang, Yi Yang, Yueting Zhuang

Diffusion models have revitalized the image generation domain, playing crucial roles in both academic research and artistic expression. With the emergence of new diffusion models, assessing the performance of text-to-image models has become increasingly important. Current metrics focus on directly matching the input text with the generated image, but due to cross-modal information asymmetry, this leads to unreliable or incomplete assessment results. Motivated by this, we introduce the Image Regeneration task in this study to assess text-to-image models by tasking the T2I model with generating an image according to the reference image. We use GPT4V to bridge the gap between the reference image and the text input for the T2I model, allowing T2I models to understand image content. This evaluation process is simplified as comparisons between the generated image and the reference image are straightforward. Two regeneration datasets spanning content-diverse and style-diverse evaluation dataset are introduced to evaluate the leading diffusion models currently available. Additionally, we present ImageRepainter framework to enhance the quality of generated images by improving content comprehension via MLLM guided iterative generation and revision. Our comprehensive experiments have showcased the effectiveness of this framework in assessing the generative capabilities of models. By leveraging MLLM, we have demonstrated that a robust T2M can produce images more closely resembling the reference image.

Hefei Mei, Minjing Dong, Chang Xu

Diffusion models (DMs) have demonstrated great potential in the field of adversarial robustness, where DM-based defense methods can achieve superior defense capability without adversarial training. However, they all require huge computational costs due to the usage of large-scale pre-trained DMs, making it difficult to conduct full evaluation under strong attacks and compare with traditional CNN-based methods. Simply reducing the network size and timesteps in DMs could significantly harm the image generation quality, which invalidates previous frameworks. To alleviate this issue, we redesign the diffusion framework from generating high-quality images to predicting distinguishable image labels. Specifically, we employ an image translation framework to learn many-to-one mapping from input samples to designed orthogonal image labels. Based on this framework, we introduce an efficient Image-to-Image diffusion classifier with a pruned U-Net structure and reduced diffusion timesteps. Besides the framework, we redesign the optimization objective of DMs to fit the target of image classification, where a new classification loss is incorporated in the DM-based image translation framework to distinguish the generated label from those of other classes. We conduct sufficient evaluations of the proposed classifier under various attacks on popular benchmarks. Extensive experiments show that our method achieves better adversarial robustness with fewer computational costs than DM-based and CNN-based methods.

Ruixin Mao, Aoyu Shen, Lin Tang, Jun Zhou

Event-based cameras feature high temporal resolution, wide dynamic range, and low power consumption, which are ideal for high-speed and low-light object detection. Spiking neural networks (SNNs) are promising for event-based object recognition and detection due to their spiking nature but lack efficient training methods, leading to gradient vanishing and high computational complexity, especially in deep SNNs. Additionally, existing SNN frameworks often fail to effectively handle multi-scale spatiotemporal features, leading to increased data redundancy and reduced accuracy. To address these issues, we propose CREST, a novel conjointly trained spike-driven framework to exploit spatiotemporal dynamics in event-based object detection. We introduce the conjoint learning rule to accelerate SNN learning and alleviate gradient vanishing. It also supports dual operation modes for efficient and flexible implementation on different hardware types. Additionally, CREST features a fully spike driven framework with a multi-scale spatiotemporal event integrator (MESTOR) and a spatiotemporal-IoU (ST-IoU) loss. Our approach achieves superior object recognition & detection performance and energy efficiency compared with state of-the-art SNN algorithms on three datasets, providing an efficient solution for event-based object detection algorithms suitable for SNN hardware implementation.

Aihua Mao, Yuxuan Tang, Jiangtao Huang, Ying He

In this paper we study the task of a single-view image-guided point cloud completion. Existing methods have got promising results by fusing the information of image into point cloud explicitly or implicitly. However, given that the image has global shape information and the partial point cloud has rich local details, We believe that both modalities need to be given equal attention when performing modality fusion. To this end, we propose a novel dual-channel modality fusion network for image-guided point cloud completion(named DMF-Net), in a coarse-to-fine manner. In the first stage, DMF-Net takes a partial point cloud and corresponding image as input to recover a coarse point cloud. In the second stage, the coarse point cloud will be upsampled twice with shape-aware upsampling transformer to get the dense and complete point cloud. Extensive quantitative and qualitative experimental results show that DMF-Net outperforms the state-of-the-art unimodal and multimodal point cloud completion works on ShapeNet-ViPC dataset.

Xinji Mai, Haoran Wang, Zeng Tao, Junxiong Lin, Shaoqi Yan, Yan Wang, Jiawen Yu, Xuan Tong, Yating Li, Wenqiang Zhang

Dynamic Facial Expression Recognition (DFER) is crucial for affective computing but often overlooks the impact of scene context. We have identified a significant issue in current DFER tasks: human annotators typically integrate emotions from various angles, including environmental cues and body language, whereas existing DFER methods tend to consider the scene as noise that needs to be filtered out, focusing solely on facial information. We refer to this as the Rigid Cognitive Problem. The Rigid Cognitive Problem can lead to discrepancies between the cognition of annotators and models in some samples. To align more closely with the human cognitive paradigm of emotions, we propose an Overall Understanding of the Scene DFER method (OUS). OUS effectively integrates scene and facial features, combining scene-specific emotional knowledge for DFER. Extensive experiments on the two largest datasets in the DFER field, DFEW and FERV39k, demonstrate that OUS significantly outperforms existing methods. By analyzing the Rigid Cognitive Problem, OUS successfully understands the complex relationship between scene context and emotional expression, closely aligning with human emotional understanding in real-world scenarios.

Huayu Mai, Rui Sun, Feng Wu

The key to semi-supervised semantic segmentation lies in how to fully exploit a large amount of unlabeled data to improve the model’s generalization performance. Most methods are lured into the trap of taking each class independently (i.e., class-independent consistency) and neglecting the fact that there exist semantic dependencies among classes. In this paper, we analyze the bottlenecks of class-independent consistency inherent in previous methods and offer a fresh perspective of cooperative game theory to explicitly encourage class-consensus alignment (i.e., class-consensus consistency between the teacher (weak augmented view) and student network (strong augmented view). We formulate classes as players in an cooperative game to model their interpretable consensus and shed light on the possibility of closer collaboration between consensus themselves and consistency regularization, yielding more comprehensive and effective supervision signals. To this end, we carefully design the class-consensus consistency without introducing any external knowledge to model class structure information which renders better interpretability, and further, prepend relaxed class-consensus consistency (RCC) to unlock the potential of modeling class consensus by relaxing the strict alignment of direct class consensus values to ranking alignment. Extensive experimental results on multiple benchmarks demonstrate that RCC performs favorably against state-of-the-art methods. Particularly in the low-data regimes, RCC achieves significant improvements.

Zhen-Xiang Ma, Zhen-Duo Chen, Tai Zheng, Xin Luo, Zixia Jia, Xin-Shun Xu

Recently, a number of effective methods have been proposed to tackle the challenging task of Few-Shot Fine-Grained Image Classification (FS-FGIC). However, how to fully leverage the backbone network to discover and extract detailed features to generate more discriminative class prototypes, as well as how to accurately model the similarity relationship between query samples and the class prototypes, are still issues to be further considered. Therefore, we propose a novel progreSsively featUre refInement and conTinuous rElationship moDeling method, SUITED for short, to address these two issues existing in the State-of-the-Art FS-FGIC methods. Specifically, we design the Progressive Feature Refinement Module (PFRM) to fully exploit the backbone network's progressive feature extraction capabilities, forming multi-scale feature representations to further enhance discriminative features. Then, the Continuous Relationship Modeling Module (CRMM) is proposed to capture the dependencies between query samples and the corresponding class prototypes, achieving precise optimization of the distances among corresponding sample points in the feature space. We conducted extensive experiments on five fine-grained benchmark datasets, and the experimental results demonstrate that the proposed method is comprehensively ahead of the existing State-of-the-Art methods.

Yuhang Ma, Wenting Xu, Chaoyi Zhao, Keqiang Sun, Qinfeng Jin, Xiaoda Yang, Zeng Zhao, Changjie Fan, Zhipeng Hu

Recent advances in text-to-image diffusion models have spurred significant interest in continuous story image generation. In this paper, we introduce Storynizor, a model capable of generating coherent stories with strong inter-frame character consistency, effective foreground-background separation, and diverse pose variation. The core innovation of Storynizor lies in its key modules: ID-Synchronizer and ID-Injector. The ID-Synchronizer employs an auto-mask self-attention module and a mask perceptual loss across inter-frame images to improve the consistency of character generation, vividly representing their postures and backgrounds. The ID-Injector utilize a Shuffling Reference Strategy (SRS) to integrate ID features into specific locations, enhancing ID-based consistent character generation. Additionally, to facilitate the training of Storynizor, we have curated a novel dataset called StoryDB comprising 100, 000 images. This dataset contains single and multiple-character sets in diverse environments, layouts, and gestures with detailed descriptions. Experimental results indicate that Storynizor demonstrates superior coherent story generation with high-fidelity character consistency, flexible postures, and vivid backgrounds compared to other character-specific methods.

Yue Ma, Yingqing He, Hongfa Wang, Andong Wang, Leqi Shen, Chenyang Qi, Jixuan Ying, Chengfei Cai, Zhifeng Li, Heung-Yeung Shum 等

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.

Xinghua Ma, Xinyan Fang, Mingye Zou, Gongning Luo, Wei Wang, Kuanquan Wang, Zhaowen Qiu, Xin Gao, Shuo Li

Coronary Artery Disease (CAD) poses a significant threat to cardiovascular patients worldwide, underscoring the critical importance of automated CAD diagnostic technologies in clinical practice. Previous technologies for lesion assessment in Coronary CT Angiography (CCTA) images have been insufficient in terms of interpretability, resulting in solutions that lack clinical reliability in both network architecture and prediction outcomes, even when diagnoses are accurate. To address the limitation of interpretability, we introduce the Trusted Lesion-Assessment Network (TLA-Net), which provides a clinically reliable solution for multi-view CAD diagnosis: (1) The causality-informed evidence collection constructs a causal graph for the diagnostic process and implements causal interventions, preventing confounders' interference and enhancing the transparency of the network architecture. (2) The clinically-aligned uncertainty integration hierarchically combines Dirichlet distributions from various views based on clinical priors, offering confidence coefficients for prediction outcomes that align with physicians' image analysis procedures. Experimental results on a dataset of 2,618 lesions demonstrate that TLA-Net, supported by its interpretable methodological design, exhibits superior performance with outstanding generalization, domain adaptability, and robustness.

Xin Ma, Jiguang Zhang, Peng Lu, Shibiao Xu, Chengwei Pan

Novel view synthesis is a critical task in autonomous driving. Although 3D Gaussian Splatting (3D-GS) has shown success in generating novel views, it faces challenges in maintaining high-quality rendering when viewpoints deviate significantly from the training set. This difficulty primarily stems from complex lighting conditions and geometric inconsistencies in texture-less regions. To address these issues, we propose an attention-based illumination model that leverages light fields from neighboring views, enhancing the realism of synthesized images. Additionally, we propose a geometry optimization method using planar homography to improve geometric consistency in texture-less regions. Our experiments demonstrate substantial improvements in synthesis quality for large-deviation viewpoints, validating the effectiveness of our approach.

Weijian Ma, Ruoxin Chen, Keyue Zhang, Shuang Wu, Shouhong Ding

Data augmentation is expected to bring about unseen features of training set, enhancing the model’s ability to generalize in situations where data is limited. Generative image models trained on large web-crawled datasets such as LAION are known to produce images with stereotypes and imperceptible bias when used to augment training data, owing to dataset misalignment and the generator’s ignorance of the downstream model. We improve downstream task awareness in generated images by proposing a task-aware fine-tuning strategy that actively detects failures of downstream task in the target model to fine-tune the generation process between epochs. The dynamic fine-tuning strategy is achieved by (1) inspecting misalignment between generated data and original data via VLM captioners and (2) adjusts both prompts and diffusion model so that the strategy dynamically guides the generator by focusing on the detected bias of VLM. This is done via re-captioning the overfitted data as well as finetuning the diffusion trajectory in a contrastive manner. To co-operate with the VLM captioner, the contrastive fine-tuning process dynamically adjusts different parts of the diffusion trajectory based on detected misalignment, thus shifting the the generated distribution away from making the downstream model overfit. Our experiments on few-shot class incremental learning show that our instruction-guided finetuning strategy consistently assists the downstream model with higher classification accuracy compared to generative data augmentation baselines such as Stable Diffusion and GPT-4o, and state-of-the-art non-generative strategies.