Enhanced Dual-Pattern Matching With Vision-Language Representation for Out-of-Distribution Detection

doi:10.1109/TPAMI.2025.3590717

	Enhanced Dual-Pattern Matching With Vision-Language Representation for Out-of-Distribution Detection
	Xiang, Xiang 1,2; Xu, Zhuo 3; Zhang, Zihan 3; Zeng, Zhigang 3; Chen, Xilin 4
	2025-11-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	47 期号:11 页码:9673-9687
摘要	Out-of-distribution (OOD) detection presents a significant challenge in deploying pattern recognition and machine learning models, as they frequently fail to generalize to data from unseen distributions. Recent advancements in vision-language models (VLMs), particularly CLIP, have demonstrated promising results in OOD detection through their rich multimodal representations. However, current CLIP-based OOD detection methods predominantly rely on single-modality in-distribution (ID) data (e.g., textual cues), overlooking the valuable information contained in ID visual cues. In this work, we demonstrate that incorporating ID visual information is crucial for unlocking CLIP's full potential in OOD detection. We propose a novel approach, Dual-Pattern Matching (DPM), which effectively adapts CLIP for OOD detection by jointly exploiting both textual and visual ID patterns. Specifically, DPM refines visual and textual features through the proposed Domain-Specific Feature Aggregation (DSFA) and Prompt Enhancement (PE) modules. Subsequently, DPM stores class-wise textual features as textual patterns and aggregates ID visual features as visual patterns. During inference, DPM calculates similarity scores relative to both patterns to identify OOD data. Furthermore, we enhance DPM with lightweight adaptation mechanisms to further boost OOD detection performance. Comprehensive experiments demonstrate that DPM surpasses state-of-the-art methods on multiple benchmarks, highlighting the effectiveness of leveraging multimodal information for OOD detection. The proposed dual-pattern approach provides a simple yet robust framework for leveraging vision-language representations in OOD detection tasks.
关键词	Visualization Adaptation models Training Data models Computational modeling Feature extraction Pattern matching Tuning Robustness Data mining OOD detection vision-language models
DOI	10.1109/TPAMI.2025.3590717
收录类别	SCI
语种	英语
资助项目	The 111 Project on Computational Intelligence and Intelligent Control[B18024] ; Foundation for Outstanding Research Groups of Hubei Province[2025AFA012] ; Peng Cheng Lab[PCL2023A08] ; Natural Science Fund of Hubei Province[2022CFB823]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001587283400007
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41621
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Xiang, Xiang
作者单位	1.Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Sch Artificial Intelligence & Automat, Wuhan 430074, Peoples R China 2.Peng Cheng Natl Lab, Shenzhen 518000, Peoples R China 3.HUST, Sch Artificial Intelligence & Automat, Wuhan 430074, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Xiang, Xiang,Xu, Zhuo,Zhang, Zihan,et al. Enhanced Dual-Pattern Matching With Vision-Language Representation for Out-of-Distribution Detection[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2025,47(11):9673-9687.
APA	Xiang, Xiang,Xu, Zhuo,Zhang, Zihan,Zeng, Zhigang,&Chen, Xilin.(2025).Enhanced Dual-Pattern Matching With Vision-Language Representation for Out-of-Distribution Detection.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,47(11),9673-9687.
MLA	Xiang, Xiang,et al."Enhanced Dual-Pattern Matching With Vision-Language Representation for Out-of-Distribution Detection".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 47.11(2025):9673-9687.