arXiv subjects

Jie Wen

Publications and source records attributed to Jie Wen.

At least 37 records · Page 2Linked to original sources

arXiv2026

Prompt Tuning for CLIP on the Pretrained Manifold

Prompt tuning introduces learnable prompt vectors that adapt pretrained vision-language models to downstream tasks in a parameter-efficient manner. However, under limited supervision, prompt tuning alters pretrained representations and drives downstream features away from the pretrained manifold toward directions that are unfavorable for transfer. This drift degrades generalization. To address this limitation, we propose ManiPT, a framework that performs prompt tuning on the pretrained manifold. ManiPT introduces cosine consistency constraints in both the text and image modalities to confine the learned representations within the pretrained geometric neighborhood. Furthermore, we introduce a structural bias that enforces incremental corrections, guiding the adaptation along transferable directions to mitigate reliance on shortcut learning. From a theoretical perspective, ManiPT alleviates overfitting tendencies under limited data. Our experiments cover four downstream settings: unseen-class generalization, few-shot classification, cross-dataset transfer, and domain generalization. Across these settings, ManiPT achieves higher average performance than baseline methods. Notably, ManiPT provides an explicit perspective on how prompt tuning overfits under limited supervision.

cs.CV↗

arXiv2026

Cross-Modal Mapping: Mitigating the Modality Gap for Few-Shot Image Classification

Few-shot image classification remains a critical challenge in the field of computer vision, particularly in data-scarce environments. Existing methods typically rely on pre-trained visual-language models, such as CLIP. However, due to the modality gap, which is the inconsistent distribution of image and text features in the joint embedding space, directly using these features as class prototypes often leads to suboptimal performance. To address this issue, we propose a novel Cross-Modal Mapping (CMM) method. This method globally aligns image features with the text feature space through linear transformation and optimizes their local spatial relationships using triplet loss, thereby significantly enhancing cross-modal consistency. Experimental results show that compared to other methods, CMM simplifies the training process and demonstrates higher efficiency. Furthermore, CMM improves the average Top-1 accuracy by 1.06% on 11 benchmark datasets compared to methods that partially fine-tune the backbone, and it performs excellently on 4 distribution shift datasets. Notably, CMM effectively mitigates the modality gap in pre-trained models, enabling text features to serve as effective class prototypes for image features, thus providing an efficient and highly generalizable solution for few-shot learning.

cs.CV↗

arXiv2026

Single Image Reflection Separation via Dual Prior Interaction Transformer

Single image reflection separation aims to separate the transmission and reflection layers from a mixed image. Existing methods typically combine general priors from pre-trained models with task-specific priors such as text prompts and reflection detection. However, the transmission prior, as the most direct task-specific prior for the target transmission layer, has not been effectively modeled or fully utilized, limiting performance in complex scenarios. To address this issue, we propose a dual-prior interaction framework based on lightweight transmission prior generation and effective prior fusion. First, we design a Local Linear Correction Network (LLCN) that finetunes pre-trained models based on the physical constraint T=SI+B, where S and B represent pixel-wise and channel-wise scaling and bias transformations. LLCN efficiently generates high-quality transmission priors with minimal parameters. Second, we construct a Dual-Prior Interaction Transformer (DPIT) that employs a dual-stream channel reorganization attention mechanism. By reorganizing features from general and transmission priors for attention computation, DPIT achieves deep fusion of both priors, fully exploiting their complementary information. Experimental results on multiple benchmark datasets demonstrate that the proposed method achieves state-of-the-art performance.

cs.CV↗

arXiv2026

Q-Hawkeye: Reliable Visual Policy Optimization for Image Quality Assessment

Image Quality Assessment (IQA) predicts perceptual quality scores consistent with human judgments. Recent RL-based IQA methods built on MLLMs focus on generating visual quality descriptions and scores, ignoring two key reliability limitations: (i) although the model's prediction stability varies significantly across training samples, existing GRPO-based methods apply uniform advantage weighting, thereby amplifying noisy signals from unstable samples in gradient updates; (ii) most works emphasize text-grounded reasoning over images while overlooking the model's visual perception ability of image content. In this paper, we propose Q-Hawkeye, an RL-based reliable visual policy optimization framework that redesigns the learning signal through unified Uncertainty-Aware Dynamic Optimization and Perception-Aware Optimization. Q-Hawkeye estimates predictive uncertainty using the variance of predicted scores across multiple rollouts and leverages this uncertainty to reweight each sample's update strength, stabilizing policy optimization. To strengthen perceptual reliability, we construct paired inputs of degraded images and their original images and introduce an Implicit Perception Loss that constrains the model to ground its quality judgments in genuine visual evidence. Extensive experiments demonstrate that Q-Hawkeye outperforms state-of-the-art methods and generalizes better across multiple datasets. Our dataset and code are available at https://github.com/AMAP-ML/Q-Hawkeye.

cs.CV↗

arXiv2026

M3-AD: Reflection-aware Multi-modal, Multi-category, and Multi-dimensional Benchmark and Framework for Industrial Anomaly Detection

Although multimodal large language models (MLLMs) have advanced industrial anomaly detection toward a zero-shot paradigm, they still tend to produce high-confidence yet unreliable decisions in fine-grained and structurally complex industrial scenarios, and lack effective self-corrective mechanisms. To address this issue, we propose M3-AD, a unified reflection-aware multimodal framework for industrial anomaly detection. M3-AD comprises two complementary data resources: M3-AD-FT, designed for reflection-aligned fine-tuning, and M3-AD-Bench, designed for systematic cross-category evaluation, together providing a foundation for reflection-aware learning and reliability assessment. Building upon this foundation, we propose RA-Monitor, which models reflection as a learnable decision revision process and guides models to perform controlled self-correction when initial judgments are unreliable, thereby improving decision robustness. Extensive experiments conducted on M3-AD-Bench demonstrate that RA-Monitor outperforms multiple open-source and commercial MLLMs in zero-shot anomaly detection and anomaly analysis tasks. Code will be released at https://github.com/Yanhui-Lee/M3-AD.

cs.LG↗

arXiv2026

Advancing Adaptive Multi-Stage Video Anomaly Reasoning: A Benchmark Dataset and Method

Recent progress in reasoning capabilities of Multimodal Large Language Models(MLLMs) has highlighted their potential for performing complex video understanding tasks. However, in the domain of Video Anomaly Detection and Understanding (VAD&U), existing MLLM-based methods are largely limited to anomaly localization or post-hoc description, lacking explicit reasoning processes, risk awareness, and decision-oriented interpretation. To address this gap, we define a new task termed Video Anomaly Reasoning (VAR), which elevates video anomaly analysis from descriptive understanding to structured, multi-stage reasoning. VAR explicitly requires models to perform progressive reasoning over anomalous events before answering anomaly-related questions, encompassing visual perception, causal interpretation, and risk-aware decision making. To support this task, we present a new dataset with 8,641 videos, where each video is annotated with diverse question types corresponding to different reasoning depths, totaling more than 50,000 samples, making it one of the largest datasets for video anomaly. The annotations are based on a structured Perception-Cognition-Action Chain-of-Thought (PerCoAct-CoT), which formalizes domain-specific reasoning priors for video anomaly understanding. This design enables systematic evaluation of multi-stage and adaptive anomaly reasoning. In addition, we propose Anomaly-Aware Group Relative Policy Optimization to further enhance reasoning reliability under weak supervision. Building upon the proposed task and dataset, we develop an end-to-end MLLM-based VAR model termed Vad-R1-Plus, which supports adaptive hierarchical reasoning and risk-aware decision making. Extensive experiments demonstrate that the proposed benchmark and method effectively advance the reasoning capabilities of MLLMs on VAR tasks, outperforming both open-source and proprietary baselines.

cs.CV↗

arXiv2025

Diffusion Model Regularized Implicit Neural Representation for CT Metal Artifact Reduction

Computed tomography (CT) images are often severely corrupted by artifacts in the presence of metals. Existing supervised metal artifact reduction (MAR) approaches suffer from performance instability on known data due to their reliance on limited paired metal-clean data, which limits their clinical applicability. Moreover, existing unsupervised methods face two main challenges: 1) the CT physical geometry is not effectively incorporated into the MAR process to ensure data fidelity; 2) traditional heuristics regularization terms cannot fully capture the abundant prior knowledge available. To overcome these shortcomings, we propose diffusion model regularized implicit neural representation framework for MAR. The implicit neural representation integrates physical constraints and imposes data fidelity, while the pre-trained diffusion model provides prior knowledge to regularize the solution. Experimental results on both simulated and clinical data demonstrate the effectiveness and generalization ability of our method, highlighting its potential to be applied to clinical settings.

cs.CV↗

arXiv2025

Enhancing Multimodal Protein Function Prediction Through Dual-Branch Dynamic Selection with Reconstructive Pre-Training

Multimodal protein features play a crucial role in protein function prediction. However, these features encompass a wide range of information, ranging from structural data and sequence features to protein attributes and interaction networks, making it challenging to decipher their complex interconnections. In this work, we propose a multimodal protein function prediction method (DSRPGO) by utilizing dynamic selection and reconstructive pre-training mechanisms. To acquire complex protein information, we introduce reconstructive pre-training to mine more fine-grained information with low semantic levels. Moreover, we put forward the Bidirectional Interaction Module (BInM) to facilitate interactive learning among multimodal features. Additionally, to address the difficulty of hierarchical multi-label classification in this task, a Dynamic Selection Module (DSM) is designed to select the feature representation that is most conducive to current protein function prediction. Our proposed DSRPGO model improves significantly in BPO, MFO, and CCO on human datasets, thereby outperforming other benchmark models.

cs.LG↗

arXiv2025

Erdős-Ko-Rado theorem and Hilton-Milner type theorem for $k$-partitions

A $k$-partition of an $n$-set $X$ is a collection of $k$ pairwise disjoint non-empty subsets whose union is $X$. A family of $k$-partitions of $X$ is called $t$-intersecting if any two of its members share at least $t$ blocks. A $t$-intersecting family is trivial if every $k$-partition in it contains $t$ fixed blocks, and is non-trivial otherwise. In this paper, we first prove that, for $n\geq L(k,t):=(t+1)+(k-t+1)\cdot\log_2(t+1)(k-t+1)$, a $t$-intersecting family with maximum size must consist of all $k$-partitions containing $t$ fixed singletons. This improves the results given by Erdős and Székely (2000), and by Kupavskii (2023). We further determine the non-trivial $t$-intersecting families of $k$-partitions with maximum size for $n \ge 2L(k,t)$, which turn out to be natural analogs of the corresponding families for finite sets. In addition, we prove a stability result.

math.CO↗

arXiv2025

A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers

Poison-only Clean-label Backdoor Attacks aim to covertly inject attacker-desired behavior into DNNs by merely poisoning the dataset without changing the labels. To effectively implant a backdoor, multiple \textbf{triggers} are proposed for various attack requirements of Attack Success Rate (ASR) and stealthiness. Additionally, sample selection enhances clean-label backdoor attacks' ASR by meticulously selecting ``hard'' samples instead of random samples to poison. Current methods 1) usually handle the sample selection and triggers in isolation, leading to severely limited improvements on both ASR and stealthiness. Consequently, attacks exhibit unsatisfactory performance on evaluation metrics when converted to PCBAs via a mere stacking of methods. Therefore, we seek to explore the bidirectional collaborative relations between the sample selection and triggers to address the above dilemma. 2) Since the strong specificity within triggers, the simple combination of sample selection and triggers fails to substantially enhance both evaluation metrics, with generalization preserved among various attacks. Therefore, we seek to propose a set of components to significantly improve both stealthiness and ASR based on the commonalities of attacks. Specifically, Component A ascertains two critical selection factors, and then makes them an appropriate combination based on the trigger scale to select more reasonable ``hard'' samples for improving ASR. Component B is proposed to select samples with similarities to relevant trigger implanted samples to promote stealthiness. Component C reassigns trigger poisoning intensity on RGB colors through distinct sensitivity of the human visual system to RGB for higher ASR, with stealthiness ensured by sample selection, including Component B. Furthermore, all components can be strategically integrated into diverse PCBAs.

cs.CR↗

arXiv2025

ViEEG: Hierarchical Visual Neural Representation for EEG Brain Decoding

Understanding and decoding brain activity into visual representations is a fundamental challenge at the intersection of neuroscience and artificial intelligence. While EEG visual decoding has shown promise due to its non-invasive, and low-cost nature, existing methods suffer from Hierarchical Neural Encoding Neglect (HNEN)-a critical limitation where flat neural representations fail to model the brain's hierarchical visual processing hierarchy. Inspired by the hierarchical organization of visual cortex, we propose ViEEG, a neuro-We further adopt hierarchical contrastive learning for EEG-CLIP representation alignment, enabling zero-shot object recognition. Extensive experiments on the THINGS-EEG dataset demonstrate that ViEEG significantly outperforms previous methods by a large margin in both subject-dependent and subject-independent settings. Results on the THINGS-MEG dataset further confirm ViEEG's generalization to different neural modalities. Our framework not only advances the performance frontier but also sets a new paradigm for EEG brain decoding. inspired framework that addresses HNEN. ViEEG decomposes each visual stimulus into three biologically aligned components-contour, foreground object, and contextual scene-serving as anchors for a three-stream EEG encoder. These EEG features are progressively integrated via cross-attention routing, simulating cortical information flow from low-level to high-level vision.

cs.CV↗

arXiv2025

PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Models

Accurate 3D scene understanding in outdoor environments heavily relies on high-quality point clouds. However, LiDAR-scanned data often suffer from extreme sparsity, severely hindering downstream 3D perception tasks. Existing point cloud upsampling methods primarily focus on individual objects, thus demonstrating limited generalization capability for complex outdoor scenes. To address this issue, we propose PVNet, a diffusion model-based point-voxel interaction framework to perform LiDAR point cloud upsampling without dense supervision. Specifically, we adopt the classifier-free guidance-based DDPMs to guide the generation, in which we employ a sparse point cloud as the guiding condition and the synthesized point clouds derived from its nearby frames as the input. Moreover, we design a voxel completion module to refine and complete the coarse voxel features for enriching the feature representation. In addition, we propose a point-voxel interaction module to integrate features from both points and voxels, which efficiently improves the environmental perception capability of each upsampled point. To the best of our knowledge, our approach is the first scene-level point cloud upsampling method supporting arbitrary upsampling rates. Extensive experiments on various benchmarks demonstrate that our method achieves state-of-the-art performance. The source code will be available at https://github.com/chengxianjing/PVNet.

cs.CV↗

arXiv2025

HeLo: Heterogeneous Multi-Modal Fusion with Label Correlation for Emotion Distribution Learning

Multi-modal emotion recognition has garnered increasing attention as it plays a significant role in human-computer interaction (HCI) in recent years. Since different discrete emotions may exist at the same time, compared with single-class emotion recognition, emotion distribution learning (EDL) that identifies a mixture of basic emotions has gradually emerged as a trend. However, existing EDL methods face challenges in mining the heterogeneity among multiple modalities. Besides, rich semantic correlations across arbitrary basic emotions are not fully exploited. In this paper, we propose a multi-modal emotion distribution learning framework, named HeLo, aimed at fully exploring the heterogeneity and complementary information in multi-modal emotional data and label correlation within mixed basic emotions. Specifically, we first adopt cross-attention to effectively fuse the physiological data. Then, an optimal transport (OT)-based heterogeneity mining module is devised to mine the interaction and heterogeneity between the physiological and behavioral representations. To facilitate label correlation learning, we introduce a learnable label embedding optimized by correlation matrix alignment. Finally, the learnable label embeddings and label correlation matrices are integrated with the multi-modal representations through a novel label correlation-driven cross-attention mechanism for accurate emotion distribution learning. Experimental results on two publicly available datasets demonstrate the superiority of our proposed method in emotion distribution learning.

cs.LG↗

arXiv2025

Weakly Supervised Visible-Infrared Person Re-Identification via Heterogeneous Expert Collaborative Consistency Learning

To reduce the reliance of visible-infrared person re-identification (ReID) models on labeled cross-modal samples, this paper explores a weakly supervised cross-modal person ReID method that uses only single-modal sample identity labels, addressing scenarios where cross-modal identity labels are unavailable. To mitigate the impact of missing cross-modal labels on model performance, we propose a heterogeneous expert collaborative consistency learning framework, designed to establish robust cross-modal identity correspondences in a weakly supervised manner. This framework leverages labeled data from each modality to independently train dedicated classification experts. To associate cross-modal samples, these classification experts act as heterogeneous predictors, predicting the identities of samples from the other modality. To improve prediction accuracy, we design a cross-modal relationship fusion mechanism that effectively integrates predictions from different experts. Under the implicit supervision provided by cross-modal identity correspondences, collaborative and consistent learning among the experts is encouraged, significantly enhancing the model's ability to extract modality-invariant features and improve cross-modal identity recognition. Experimental results on two challenging datasets validate the effectiveness of the proposed method.

cs.CV↗

arXiv2025

Reliable Representation Learning for Incomplete Multi-View Missing Multi-Label Classification

As a cross-topic of multi-view learning and multi-label classification, multi-view multi-label classification has gradually gained traction in recent years. The application of multi-view contrastive learning has further facilitated this process, however, the existing multi-view contrastive learning methods crudely separate the so-called negative pair, which largely results in the separation of samples belonging to the same category or similar ones. Besides, plenty of multi-view multi-label learning methods ignore the possible absence of views and labels. To address these issues, in this paper, we propose an incomplete multi-view missing multi-label classification network named RANK. In this network, a label-driven multi-view contrastive learning strategy is proposed to leverage supervised information to preserve the intra-view structure and perform the cross-view consistency alignment. Furthermore, we break through the view-level weights inherent in existing methods and propose a quality-aware sub-network to dynamically assign quality scores to each view of each sample. The label correlation information is fully utilized in the final multi-label cross-entropy classification loss, effectively improving the discriminative power. Last but not least, our model is not only able to handle complete multi-view multi-label data, but also works on datasets with missing instances and labels. Extensive experiments confirm that our RANK outperforms existing state-of-the-art methods.

cs.CV↗

arXiv2025

Federated Incomplete Multi-view Clustering with Globally Fused Graph Guidance

Federated multi-view clustering has been proposed to mine the valuable information within multi-view data distributed across different devices and has achieved impressive results while preserving the privacy. Despite great progress, most federated multi-view clustering methods only used global pseudo-labels to guide the downstream clustering process and failed to exploit the global information when extracting features. In addition, missing data problem in federated multi-view clustering task is less explored. To address these problems, we propose a novel Federated Incomplete Multi-view Clustering method with globally Fused Graph guidance (FIMCFG). Specifically, we designed a dual-head graph convolutional encoder at each client to extract two kinds of underlying features containing global and view-specific information. Subsequently, under the guidance of the fused graph, the two underlying features are fused into high-level features, based on which clustering is conducted under the supervision of pseudo-labeling. Finally, the high-level features are uploaded to the server to refine the graph fusion and pseudo-labeling computation. Extensive experimental results demonstrate the effectiveness and superiority of FIMCFG. Our code is publicly available at https://github.com/PaddiHunter/FIMCFG.

cs.LG↗

arXiv2025

Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought

Recent advancements in reasoning capability of Multimodal Large Language Models (MLLMs) demonstrate its effectiveness in tackling complex visual tasks. However, existing MLLM-based Video Anomaly Detection (VAD) methods remain limited to shallow anomaly descriptions without deep reasoning. In this paper, we propose a new task named Video Anomaly Reasoning (VAR), which aims to enable deep analysis and understanding of anomalies in the video by requiring MLLMs to think explicitly before answering. To this end, we propose Vad-R1, an end-to-end MLLM-based framework for VAR. Specifically, we design a Perception-to-Cognition Chain-of-Thought (P2C-CoT) that simulates the human process of recognizing anomalies, guiding the MLLM to reason anomaly step-by-step. Based on the structured P2C-CoT, we construct Vad-Reasoning, a dedicated dataset for VAR. Furthermore, we propose an improved reinforcement learning algorithm AVA-GRPO, which explicitly incentivizes the anomaly reasoning capability of MLLMs through a self-verification mechanism with limited annotations. Experimental results demonstrate that Vad-R1 achieves superior performance, outperforming both open-source and proprietary models on VAD and VAR tasks. Codes and datasets will be released at https://github.com/wbfwonderful/Vad-R1.

cs.CV↗

arXiv2025

State of health prediction of lithium-ion batteries for driving conditions based on full parameter domain sparrow search algorithm and dual-module bidirectional gated recurrent unit

Aiming at the state of health (SOH) prediction of lithium-ion batteries (LiBs) for electric vehicles (EVs), this paper proposes a fusion model of a dual-module bidirectional gated recurrent unit (BiGRU) and sparrow search algorithm (SSA) with full parameter domain optimization. With the help of Spearman correlation analysis and ablation experiments, the indirect health indicator (HI) that can characterize the battery degradation is extracted first based on the incremental capacity (IC) curves of the Oxford battery dataset, which simulates the driving conditions. On this basis, the filtered one-dimensional HI is inputted into the dual-module BiGRU for learning the pre- and post-textual information of the input sequence and extracting the sequence features. In order to combine the different hyperparameters in the dual-module BiGRU, SSA is used to optimize the hyperparameters in the full parameter domain. The proposed SSA-BiGRU model combines the advantages and structures of SSA and BiGRU to achieve the highly accurate SOH prediction of LiBs. Studies based on the Oxford battery dataset have shown that the SSA-BiGRU model has higher accuracy, better robustness and generalization ability. Moreover, the proposed SSA-BiGRU model is tested on a real road-driven EV charging dataset and accurate SOH prediction are obtained.

eess.SY↗