Aihua Zheng

Shihao Li, Huaibo Huang, Junxian Duan et al.

Multi-modal object Re-IDentification (ReID) aims to obtain complete identity features across heterogeneous modalities. However, most existing methods rely on implicit feature fusion modules, making it difficult to model fine-grained recognition patterns under various challenges in real world. Benefiting from the powerful Multi-modal Large Language Models (MLLMs), the object appearances are effectively translated into descriptive captions. In this paper, we propose a reliable caption generation pipeline based on attribute confidence, which significantly reduces the unknown recognition rate of MLLMs and improves the quality of generated text. Additionally, to model diverse identity patterns, we propose a novel ReID framework, named NEXT, the Multi-grained Mixture of Experts via Text-Modulation for Multi-modal Object Re-Identification. Specifically, we decouple the recognition problem into semantic and structural branches to separately capture fine-grained appearance features and coarsegrained structure features. For semantic recognition, we first propose a Text-Modulated Semantic Experts (TMSE), which randomly samples high-quality captions to modulate experts capturing semantic features and mining inter-modality complementary cues. Second, to recognize structure features, we propose a Context-Shared Structure Experts (CSSE), which focuses on the holistic object structure and maintains identity structural consistency via a soft routing mechanism. Finally, we propose a Multi-Grained Features Aggregation (MGFA), which adopts a unified fusion strategy to effectively integrate multi-grained expert features into the final identity representations. Extensive experiments on two public person datasets and three vehicle datasets demonstrate the effectiveness of our method, showing that it significantly outperforms existing state-of-the-art methods.

Yuhao Wang, Xuehu Liu, Tianyu Yan et al.

Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by utilizing complementary image information from different modalities. Recently, large-scale pre-trained models like CLIP have demonstrated impressive performance in traditional single-modal object ReID tasks. However, they remain unexplored for multi-modal object ReID. Furthermore, current multi-modal aggregation methods have obvious limitations in dealing with long sequences from different modalities. To address above issues, we introduce a novel framework called MambaPro for multi-modal object ReID. To be specific, we first employ a Parallel Feed-Forward Adapter (PFA) for adapting CLIP to multi-modal object ReID. Then, we propose the Synergistic Residual Prompt (SRP) to guide the joint learning of multi-modal features. Finally, leveraging Mamba's superior scalability for long sequences, we introduce Mamba Aggregation (MA) to efficiently model interactions between different modalities. As a result, MambaPro could extract more robust features with lower complexity. Extensive experiments on three multi-modal object ReID benchmarks (i.e., RGBNT201, RGBNT100 and MSVR310) validate the effectiveness of our proposed methods. The source code is available at https://github.com/924973292/MambaPro.

Yuhe Ding, Bo Jiang, Lijun Sheng et al.

Transferability estimation aims to provide heuristics for quantifying how suitable a pre-trained model is for a specific downstream task, without fine-tuning them all. Prior studies have revealed that well-trained models exhibit the phenomenon of Neural Collapse. Based on a widely used neural collapse metric in existing literature, we observe a strong correlation between the neural collapse of pre-trained models and their corresponding fine-tuned models. Inspired by this observation, we propose a novel method termed Fair Collapse (FaCe) for transferability estimation by comprehensively measuring the degree of neural collapse in the pre-trained model. Typically, FaCe comprises two different terms: the variance collapse term, which assesses the class separation and within-class compactness, and the class fairness term, which quantifies the fairness of the pre-trained model towards each class. We investigate FaCe on a variety of pre-trained classification models across different network architectures, source datasets, and training loss functions. Results show that FaCe yields state-of-the-art performance on different tasks including image classification, semantic segmentation, and text classification, which demonstrate the effectiveness and generalization of our method.

Xixi Wan, Aihua Zheng, Bo Jiang et al.

Multi-modal object Re-IDentification (ReID) has gained considerable attention with the goal of retrieving specific targets across cameras using heterogeneous visual data sources. At present, multi-modal object ReID faces two core challenges: (1) learning robust features under fine-grained local noise caused by occlusion, frame loss, and other disruptions; and (2) effectively integrating heterogeneous modalities to enhance multi-modal representation. To address the above challenges, we propose a robust approach named Uncertainty-Guided Graph model for multi-modal object ReID (UGG-ReID). UGG-ReID is designed to mitigate noise interference and facilitate effective multi-modal fusion by estimating both local and sample-level aleatoric uncertainty and explicitly modeling their dependencies. Specifically, we first propose the Gaussian patch-graph representation model that leverages uncertainty to quantify fine-grained local cues and capture their structural relationships. This process boosts the expressiveness of modal-specific information, ensuring that the generated embeddings are both more informative and robust. Subsequently, we design an uncertainty-guided mixture of experts strategy that dynamically routes samples to experts exhibiting low uncertainty. This strategy effectively suppresses noise-induced instability, leading to enhanced robustness. Meanwhile, we design an uncertainty-guided routing to strengthen the multi-modal interaction, improving the performance. UGG-ReID is comprehensively evaluated on five representative multi-modal object ReID datasets, encompassing diverse spectral modalities. Experimental results show that the proposed method achieves excellent performance on all datasets and is significantly better than current methods in terms of noise immunity. Our code is available at https://github.com/wanxixi11/UGG-ReID.

Bo Jiang, Sheng Wang, Xiao Wang et al.

Recently, Batch DropBlock network (BDB) has demonstrated its effectiveness on person image representation and re-identification task via feature erasing. However, BDB drops the features \textbf{randomly} which may lead to sub-optimal results. In this paper, we propose a novel Self-Thresholding attention guided Adaptive DropBlock network (STADB) for person re-ID which can \textbf{adaptively} erase the most discriminative regions. Specifically, STADB first obtains an attention map by channel-wise pooling and returns a drop mask by thresholding the attention map. Then, the input features and self-thresholding attention guided drop mask are multiplied to generate the dropped feature maps. In addition, STADB utilizes the spatial and channel attention to learn a better feature map and iteratively trains the feature dropping module for person re-ID. Experiments on several benchmark datasets demonstrate that the proposed STADB outperforms many other related methods for person re-ID. The source code of this paper is released at: \textcolor{red}{\url{https://github.com/wangxiao5791509/STADB_ReID}}.

Yuhe Ding, Bo Jiang, Aijing Yu et al.

Transfer learning methods endeavor to leverage relevant knowledge from existing source pre-trained models or datasets to solve downstream target tasks. With the increase in the scale and quantity of available pre-trained models nowadays, it becomes critical to assess in advance whether they are suitable for a specific target task. Model transferability estimation is an emerging and growing area of interest, aiming to propose a metric to quantify this suitability without training them individually, which is computationally prohibitive. Despite extensive recent advances already devoted to this area, they have custom terminological definitions and experimental settings. In this survey, we present the first review of existing advances in this area and categorize them into two separate realms: source-free model transferability estimation and source-dependent model transferability estimation. Each category is systematically defined, accompanied by a comprehensive taxonomy. Besides, we address challenges and outline future research directions, intending to provide a comprehensive guide to aid researchers and practitioners.

Yuhe Ding, Jian Liang, Bo Jiang et al.

CLIP-based domain generalization aims to improve model generalization to unseen domains by leveraging the powerful zero-shot classification capabilities of CLIP and multiple source datasets. Existing methods typically train a single model across multiple source domains to capture domain-shared information. However, this paradigm inherently suffers from two types of conflicts: 1) sample conflicts, arising from noisy samples and extreme domain shifts among sources; and 2) optimization conflicts, stemming from competition and trade-offs during multi-source training. Both hinder the generalization and lead to suboptimal solutions. Recent studies have shown that model merging can effectively mitigate the competition of multi-objective optimization and improve generalization performance. Inspired by these findings, we propose Harmonizing and Merging (HAM), a novel source model merging framework for CLIP-based domain generalization. During the training process of the source models, HAM enriches the source samples without conflicting samples, and harmonizes the update directions of all models. Then, a redundancy-aware historical model merging method is introduced to effectively integrate knowledge across all source models. HAM comprehensively consolidates source domain information while enabling mutual enhancement among source models, ultimately yielding a final model with optimal generalization capabilities. Extensive experiments on five widely used benchmark datasets demonstrate the effectiveness of our approach, achieving state-of-the-art performance.

Yuhe Ding, Bo Jiang, Aihua Zheng et al.

Vision language models (VLMs) like CLIP show stellar zero-shot capability on classification benchmarks. However, selecting the VLM with the highest performance on the unlabeled downstream task is non-trivial. Existing VLM selection methods focus on the class-name-only setting, relying on a supervised large-scale dataset and large language models, which may not be accessible or feasible during deployment. This paper introduces the problem of \textbf{unsupervised vision-language model selection}, where only unsupervised downstream datasets are available, with no additional information provided. To solve this problem, we propose a method termed Visual-tExtual Graph Alignment (VEGA), to select VLMs without any annotations by measuring the alignment of the VLM between the two modalities on the downstream task. VEGA is motivated by the pretraining paradigm of VLMs, which aligns features with the same semantics from the visual and textual modalities, thereby mapping both modalities into a shared representation space. Specifically, we first construct two graphs on the vision and textual features, respectively. VEGA is then defined as the overall similarity between the visual and textual graphs at both node and edge levels. Extensive experiments across three different benchmarks, covering a variety of application scenarios and downstream datasets, demonstrate that VEGA consistently provides reliable and accurate estimates of VLMs' performance on unlabeled downstream tasks.

Aihua Zheng, Xia Sun, Chenglong Li et al.

Vehicle re-identification (Re-ID) is an active task due to its importance in large-scale intelligent monitoring in smart cities. Despite the rapid progress in recent years, most existing methods handle vehicle Re-ID task in a supervised manner, which is both time and labor-consuming and limits their application to real-life scenarios. Recently, unsupervised person Re-ID methods achieve impressive performance by exploring domain adaption or clustering-based techniques. However, one cannot directly generalize these methods to vehicle Re-ID since vehicle images present huge appearance variations in different viewpoints. To handle this problem, we propose a novel viewpoint-aware clustering algorithm for unsupervised vehicle Re-ID. In particular, we first divide the entire feature space into different subspaces according to the predicted viewpoints and then perform a progressive clustering to mine the accurate relationship among samples. Comprehensive experiments against the state-of-the-art methods on two multi-viewpoint benchmark datasets VeRi and VeRi-Wild validate the promising performance of the proposed method in both with and without domain adaption scenarios while handling unsupervised vehicle Re-ID.

Yuhe Ding, Xin Ma, Mandi Luo et al.

Photo-to-caricature translation aims to synthesize the caricature as a rendered image exaggerating the features through sketching, pencil strokes, or other artistic drawings. Style rendering and geometry deformation are the most important aspects in photo-to-caricature translation task. To take both into consideration, we propose an unsupervised contrastive photo-to-caricature translation architecture. Considering the intuitive artifacts in the existing methods, we propose a contrastive style loss for style rendering to enforce the similarity between the style of rendered photo and the caricature, and simultaneously enhance its discrepancy to the photos. To obtain an exaggerating deformation in an unpaired/unsupervised fashion, we propose a Distortion Prediction Module (DPM) to predict a set of displacements vectors for each input image while fixing some controlling points, followed by the thin plate spline interpolation for warping. The model is trained on unpaired photo and caricature while can offer bidirectional synthesizing via inputting either a photo or a caricature. Extensive experiments demonstrate that the proposed model is effective to generate hand-drawn like caricatures compared with existing competitors.

Hao Zhu, Yi Li, Feixia Zhu et al.

We propose a new task named Audio-driven Per-formance Video Generation (APVG), which aims to synthesizethe video of a person playing a certain instrument guided bya given music audio clip. It is a challenging task to gener-ate the high-dimensional temporal consistent videos from low-dimensional audio modality. In this paper, we propose a multi-staged framework to achieve this new task to generate realisticand synchronized performance video from given music. Firstly,we provide both global appearance and local spatial informationby generating the coarse videos and keypoints of body and handsfrom a given music respectively. Then, we propose to transformthe generated keypoints to heatmap via a differentiable spacetransformer, since the heatmap offers more spatial informationbut is harder to generate directly from audio. Finally, wepropose a Structured Temporal UNet (STU) to extract bothintra-frame structured information and inter-frame temporalconsistency. They are obtained via graph-based structure module,and CNN-GRU based high-level temporal module respectively forfinal video generation. Comprehensive experiments validate theeffectiveness of our proposed framework.

Hao Zhu, Mandi Luo, Rui Wang et al.

Audio-visual learning, aimed at exploiting the relationship between audio and visual modalities, has drawn considerable attention since deep learning started to be used successfully. Researchers tend to leverage these two modalities either to improve the performance of previously considered single-modality tasks or to address new challenging problems. In this paper, we provide a comprehensive survey of recent audio-visual learning development. We divide the current audio-visual learning tasks into four different subfields: audio-visual separation and localization, audio-visual correspondence learning, audio-visual generation, and audio-visual representation learning. State-of-the-art methods as well as the remaining challenges of each subfield are further discussed. Finally, we summarize the commonly used datasets and performance metrics.

Chenglong Li, Andong Lu, Aihua Zheng et al.

The task of RGBT tracking aims to take the complementary advantages from visible spectrum and thermal infrared data to achieve robust visual tracking, and receives more and more attention in recent years. Existing works focus on modality-specific information integration by introducing modality weights to achieve adaptive fusion or learning robust feature representations of different modalities. Although these methods could effectively deploy the modality-specific properties, they ignore the potential values of modality-shared cues as well as instance-aware information, which are crucial for effective fusion of different modalities in RGBT tracking. In this paper, we propose a novel Multi-Adapter convolutional Network (MANet) to jointly perform modality-shared, modality-specific and instance-aware feature learning in an end-to-end trained deep framework for RGBT tracking. We design three kinds of adapters within our network. In a specific, the generality adapter is to extract shared object representations, the modality adapter aims at encoding modality-specific information to deploy their complementary advantages, and the instance adapter is to model the appearance properties and temporal variations of a certain object. Moreover, to reduce computational complexity for real-time demand of visual tracking, we design a parallel structure of generic adapter and modality adapter. Extensive experiments on two RGBT tracking benchmark datasets demonstrate the outstanding performance of the proposed tracker against other state-of-the-art RGB and RGBT tracking algorithms.

Hongchao Li, Xianmin Lin, Aihua Zheng et al.

Vehicle Re-ID has recently attracted enthusiastic attention due to its potential applications in smart city and urban surveillance. However, it suffers from large intra-class variation caused by view variations and illumination changes, and inter-class similarity especially for different identities with the similar appearance. To handle these issues, in this paper, we propose a novel deep network architecture, which guided by meaningful attributes including camera views, vehicle types and colors for vehicle Re-ID. In particular, our network is end-to-end trained and contains three subnetworks of deep features embedded by the corresponding attributes (i.e., camera view, vehicle type and vehicle color). Moreover, to overcome the shortcomings of limited vehicle images of different views, we design a view-specified generative adversarial network to generate the multi-view vehicle images. For network training, we annotate the view labels on the VeRi-776 dataset. Note that one can directly adopt the pre-trained view (as well as type and color) subnetwork on the other datasets with only ID information, which demonstrates the generalization of our model. Extensive experiments on the benchmark datasets VeRi-776 and VehicleID suggest that the proposed approach achieves the promising performance and yields to a new state-of-the-art for vehicle Re-ID.

Hao Zhu, Huaibo Huang, Yi Li et al.

Talking face generation aims to synthesize a face video with precise lip synchronization as well as a smooth transition of facial motion over the entire video via the given speech clip and facial image. Most existing methods mainly focus on either disentangling the information in a single image or learning temporal information between frames. However, cross-modality coherence between audio and video information has not been well addressed during synthesis. In this paper, we propose a novel arbitrary talking face generation framework by discovering the audio-visual coherence via the proposed Asymmetric Mutual Information Estimator (AMIE). In addition, we propose a Dynamic Attention (DA) block by selectively focusing the lip area of the input image during the training stage, to further enhance lip synchronization. Experimental results on benchmark LRW dataset and GRID dataset transcend the state-of-the-art methods on prevalent metrics with robust high-resolution synthesizing on gender and pose variations.

Chenglong Li, Guizhao Wang, Yunpeng Ma et al.

Despite significant progress, image saliency detection still remains a challenging task in complex scenes and environments. Integrating multiple different but complementary cues, like RGB and Thermal (RGB-T), may be an effective way for boosting saliency detection performance. The current research in this direction, however, is limited by the lack of a comprehensive benchmark. This work contributes such a RGB-T image dataset, which includes 821 spatially aligned RGB-T image pairs and their ground truth annotations for saliency detection purpose. The image pairs are with high diversity recorded under different scenes and environmental conditions, and we annotate 11 challenges on these image pairs for performing the challenge-sensitive analysis for different saliency detection algorithms. We also implement 3 kinds of baseline methods with different modality inputs to provide a comprehensive comparison platform. With this benchmark, we propose a novel approach, multi-task manifold ranking with cross-modality consistency, for RGB-T saliency detection. In particular, we introduce a weight for each modality to describe the reliability, and integrate them into the graph-based manifold ranking algorithm to achieve adaptive fusion of different source data. Moreover, we incorporate the cross-modality consistent constraints to integrate different modalities collaboratively. For the optimization, we design an efficient algorithm to iteratively solve several subproblems with closed-form solutions. Extensive experiments against other baseline methods on the newly created benchmark demonstrate the effectiveness of the proposed approach, and we also provide basic insights and potential future research directions for RGB-T saliency detection.