Jiayi Lyu

Guoyang Xie, Jinbao Wang, Jiaqi Liu et al.

Image anomaly detection (IAD) is an emerging and vital computer vision task in industrial manufacturing (IM). Recently, many advanced algorithms have been reported, but their performance deviates considerably with various IM settings. We realize that the lack of a uniform IM benchmark is hindering the development and usage of IAD methods in real-world applications. In addition, it is difficult for researchers to analyze IAD algorithms without a uniform benchmark. To solve this problem, we propose a uniform IM benchmark, for the first time, to assess how well these algorithms perform, which includes various levels of supervision (unsupervised versus fully supervised), learning paradigms (few-shot, continual and noisy label), and efficiency (memory usage and inference speed). Then, we construct a comprehensive image anomaly detection benchmark (IM-IAD), which includes 19 algorithms on seven major datasets with a uniform setting. Extensive experiments (17,017 total) on IM-IAD provide in-depth insights into IAD algorithm redesign or selection. Moreover, the proposed IM-IAD benchmark challenges existing algorithms and suggests future research directions. To foster reproducibility and accessibility, the source code of IM-IAD is uploaded on the website, https://github.com/M-3LAB/IM-IAD.

Xing Lan, Jiayi Lyu, Hanyu Jiang et al.

In this paper, we explore the zero-shot capability of the Segment Anything Model (SAM) for food image segmentation. To address the lack of class-specific information in SAM-generated masks, we propose a novel framework, called FoodSAM. This innovative approach integrates the coarse semantic mask with SAM-generated masks to enhance semantic segmentation quality. Besides, we recognize that the ingredients in food can be supposed as independent individuals, which motivated us to perform instance segmentation on food images. Furthermore, FoodSAM extends its zero-shot capability to encompass panoptic segmentation by incorporating an object detector, which renders FoodSAM to effectively capture non-food object information. Drawing inspiration from the recent success of promptable segmentation, we also extend FoodSAM to promptable segmentation, supporting various prompt variants. Consequently, FoodSAM emerges as an all-encompassing solution capable of segmenting food items at multiple levels of granularity. Remarkably, this pioneering framework stands as the first-ever work to achieve instance, panoptic, and promptable segmentation on food images. Extensive experiments demonstrate the feasibility and impressing performance of FoodSAM, validating SAM's potential as a prominent and influential tool within the domain of food image segmentation. We release our code at https://github.com/jamesjg/FoodSAM.

Guoyang Xie, Jinbao Wang, Yawen Huang et al.

The problem of how to assess cross-modality medical image synthesis has been largely unexplored. The most used measures like PSNR and SSIM focus on analyzing the structural features but neglect the crucial lesion location and fundamental k-space speciality of medical images. To overcome this problem, we propose a new metric K-CROSS to spur progress on this challenging problem. Specifically, K-CROSS uses a pre-trained multi-modality segmentation network to predict the lesion location, together with a tumor encoder for representing features, such as texture details and brightness intensities. To further reflect the frequency-specific information from the magnetic resonance imaging principles, both k-space features and vision features are obtained and employed in our comprehensive encoders with a frequency reconstruction penalty. The structure-shared encoders are designed and constrained with a similarity loss to capture the intrinsic common structural information for both modalities. As a consequence, the features learned from lesion regions, k-space, and anatomical structures are all captured, which serve as our quality evaluators. We evaluate the performance by constructing a large-scale cross-modality neuroimaging perceptual similarity (NIRPS) dataset with 6,000 radiologist judgments. Extensive experiments demonstrate that the proposed method outperforms other metrics, especially in comparison with the radiologists on NIRPS.

Jiayi Lyu, Leigang Qu, Wenjing Zhang et al.

Realistic talking-head video generation is critical for virtual avatars, film production, and interactive systems. Current methods struggle with nuanced emotional expressions due to the lack of fine-grained emotion control. To address this issue, we introduce a novel two-stage method (AUHead) to disentangle fine-grained emotion control, i.e. , Action Units (AUs), from audio and achieve controllable generation. In the first stage, we explore the AU generation abilities of large audio-language models (ALMs), by spatial-temporal AU tokenization and an "emotion-then-AU" chain-of-thought mechanism. It aims to disentangle AUs from raw speech, effectively capturing subtle emotional cues. In the second stage, we propose an AU-driven controllable diffusion model that synthesizes realistic talking-head videos conditioned on AU sequences. Specifically, we first map the AU sequences into the structured 2D facial representation to enhance spatial fidelity, and then model the AU-vision interaction within cross-attention modules. To achieve flexible AU-quality trade-off control, we introduce an AU disentanglement guidance strategy during inference, further refining the emotional expressiveness and identity consistency of the generated videos. Results on benchmark datasets demonstrate that our approach achieves competitive performance in emotional realism, accurate lip synchronization, and visual coherence, significantly surpassing existing techniques. Our implementation is available at https://github.com/laura990501/AUHead_ICLR

Enyi Shi, Pengyang Shao, Yanxin Zhang et al.

Robust safety of vision-language large models (VLLMs) under joint multilingual and multimodal inputs remains underexplored. Existing benchmarks are typically multilingual but text-only, or multimodal but monolingual. Recent multilingual multimodal red-teaming efforts render harmful prompts into images, yet rely heavily on typography-style visuals and lack semantically grounded image-text pairs, limiting coverage of realistic cross-modal interactions. We introduce Lingua-SafetyBench, a benchmark of 100,440 harmful image-text pairs across 10 languages, explicitly partitioned into image-dominant and text-dominant subsets to disentangle risk sources. Evaluating 11 open-source VLLMs reveals a consistent asymmetry: image-dominant risks yield higher ASR in high-resource languages, while text-dominant risks are more severe in non-high-resource languages. A controlled study on the Qwen series shows that scaling and version upgrades reduce Attack Success Rate (ASR) overall but disproportionately benefit HRLs, widening the gap between HRLs and Non-HRLs under text-dominant risks. This underscores the necessity of language- and modality-aware safety alignment beyond mere scaling.To facilitate reproducibility and future research, we will publicly release our benchmark, model checkpoints, and source code.The code and dataset will be available at https://github.com/zsxr15/Lingua-SafetyBench.Warning: this paper contains examples with unsafe content.

Guohong Hu, Xing Lan, Hanyu Jiang et al.

Facial Action Units (AUs) are of great significance in the realm of affective computing. In this paper, we propose AU-LLaVA, the first unified AU recognition framework based on the Large Language Model (LLM). AU-LLaVA consists of a visual encoder, a linear projector layer, and a pre-trained LLM. We meticulously craft the text descriptions and fine-tune the model on various AU datasets, allowing it to generate different formats of AU recognition results for the same input image. On the BP4D and DISFA datasets, AU-LLaVA delivers the most accurate recognition results for nearly half of the AUs. Our model achieves improvements of F1-score up to 11.4% in specific AU recognition compared to previous benchmark results. On the FEAFA dataset, our method achieves significant improvements over all 24 AUs compared to previous benchmark results. AU-LLaVA demonstrates exceptional performance and versatility in AU recognition.

Tanzhe Li, Caoshuo Li, Jiayi Lyu et al.

State space models (SSMs) have recently garnered significant attention in computer vision. However, due to the unique characteristics of image data, adapting SSMs from natural language processing to computer vision has not outperformed the state-of-the-art convolutional neural networks (CNNs) and Vision Transformers (ViTs). Existing vision SSMs primarily leverage manually designed scans to flatten image patches into sequences locally or globally. This approach disrupts the original semantic spatial adjacency of the image and lacks flexibility, making it difficult to capture complex image structures. To address this limitation, we propose Dynamic Adaptive Scan (DAS), a data-driven method that adaptively allocates scanning orders and regions. This enables more flexible modeling capabilities while maintaining linear computational complexity and global modeling capacity. Based on DAS, we further propose the vision backbone DAMamba, which significantly outperforms current state-of-the-art vision Mamba models in vision tasks such as image classification, object detection, instance segmentation, and semantic segmentation. Notably, it surpasses some of the latest state-of-the-art CNNs and ViTs. Code will be available at https://github.com/ltzovo/DAMamba.

Guoyang Xie, Yawen Huang, Jinbao Wang et al.

Multi-modality imaging improves disease diagnosis and reveals distinct deviations in tissues with anatomical properties. The existence of completely aligned and paired multi-modality neuroimaging data has proved its effectiveness in brain research. However, collecting fully aligned and paired data is expensive or even impractical, since it faces many difficulties, including high cost, long acquisition time, image corruption, and privacy issues. An alternative solution is to explore unsupervised or weakly supervised learning methods to synthesize the absent neuroimaging data. In this paper, we provide a comprehensive review of cross-modality synthesis for neuroimages, from the perspectives of weakly supervised and unsupervised settings, loss functions, evaluation metrics, imaging modalities, datasets, and downstream applications based on synthesis. We begin by highlighting several opening challenges for cross-modality neuroimage synthesis. Then, we discuss representative architectures of cross-modality synthesis methods under different supervisions. This is followed by a stepwise in-depth analysis to evaluate how cross-modality neuroimage synthesis improves the performance of its downstream tasks. Finally, we summarize the existing research findings and point out future research directions. All resources are available at https://github.com/M-3LAB/awesome-multimodal-brain-image-systhesis

Jinbao Wang, Guoyang Xie, Yawen Huang et al.

Utilizing multi-modal neuroimaging data has been proved to be effective to investigate human cognitive activities and certain pathologies. However, it is not practical to obtain the full set of paired neuroimaging data centrally since the collection faces several constraints, e.g., high examination cost, long acquisition time, and image corruption. In addition, these data are dispersed into different medical institutions and thus cannot be aggregated for centralized training considering the privacy issues. There is a clear need to launch a federated learning and facilitate the integration of the dispersed data from different institutions. In this paper, we propose a new benchmark for federated domain translation on unsupervised brain image synthesis (termed as FedMed-GAN) to bridge the gap between federated learning and medical GAN. FedMed-GAN mitigates the mode collapse without sacrificing the performance of generators, and is widely applied to different proportions of unpaired and paired data with variation adaptation property. We treat the gradient penalties by federally averaging algorithm and then leveraging differential privacy gradient descent to regularize the training dynamics. A comprehensive evaluation is provided for comparing FedMed-GAN and other centralized methods, which shows the new state-of-the-art performance by our FedMed-GAN. Our code has been released on the website: https://github.com/M-3LAB/FedMed-GAN

Wei Gan, Jian Xue, Ke Lu et al.

Nearly all existing Facial Action Coding System-based datasets that include facial action unit (AU) intensity information annotate the intensity values hierarchically using A--E levels. However, facial expressions change continuously and shift smoothly from one state to another. Therefore, it is more effective to regress the intensity value of local facial AUs to represent whole facial expression changes, particularly in the fields of expression transfer and facial animation. We introduce an extension of FEAFA in combination with the relabeled DISFA database, which is available at https://www.iiplab.net/feafa+/ now. Extended FEAFA (FEAFA+) includes 150 video sequences from FEAFA and DISFA, with a total of 230,184 frames being manually annotated on floating-point intensity value of 24 redefined AUs using the Expression Quantitative Tool. We also list crude numerical results for posed and spontaneous subsets and provide a baseline comparison for the AU intensity regression task.

Yanfu Yan, Ke Lu, Jian Xue et al.

Facial expression analysis based on machine learning requires large number of well-annotated data to reflect different changes in facial motion. Publicly available datasets truly help to accelerate research in this area by providing a benchmark resource, but all of these datasets, to the best of our knowledge, are limited to rough annotations for action units, including only their absence, presence, or a five-level intensity according to the Facial Action Coding System. To meet the need for videos labeled in great detail, we present a well-annotated dataset named FEAFA for Facial Expression Analysis and 3D Facial Animation. One hundred and twenty-two participants, including children, young adults and elderly people, were recorded in real-world conditions. In addition, 99,356 frames were manually labeled using Expression Quantitative Tool developed by us to quantify 9 symmetrical FACS action units, 10 asymmetrical (unilateral) FACS action units, 2 symmetrical FACS action descriptors and 2 asymmetrical FACS action descriptors, and each action unit or action descriptor is well-annotated with a floating point number between 0 and 1. To provide a baseline for use in future research, a benchmark for the regression of action unit values based on Convolutional Neural Networks are presented. We also demonstrate the potential of our FEAFA dataset for 3D facial animation. Almost all state-of-the-art algorithms for facial animation are achieved based on 3D face reconstruction. We hence propose a novel method that drives virtual characters only based on action unit value regression of the 2D video frames of source actors.