中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 紫东太初大模型研究中心
  5. 大模型计算
Learning enhancing modality-invariant features for visible-infrared person re-identification

文献类型：期刊论文

作者Zhang, La1; Zhao, Xu2; Du, Haohua3; Sun, Jian1; Wang, Jinqiao2
刊名INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
出版日期2024-04-22
页码19
关键词Visible-infrared person re-identification Cross-modality Feature learning Feature distribution
ISSN号1868-8071
DOI10.1007/s13042-024-02168-6
通讯作者Zhao, Xu(xu.zhao@nlpr.ia.ac.cn)
英文摘要To solve the task of visible-infrared person re-identification, most existing methods embed all images into a unified feature space through shared parameters, and then use a metric learning loss function to learn modality-invariant features. However, they may encounter the following two problems: For one thing, they mostly focus on modality-invariant features. In reality, some unique features within each modality can enhance feature discriminability but are often overlooked; For another, current metric learning loss functions mainly focus on feature discriminability and only align modality distributions implicitly, which leads to that the feature distributions from different modalities are still inconsistent in this unified feature space. Taking the foregoing into consideration, in this paper, we propose a novel end-to-end framework composed of two modules: the intra-modality enhancing module and the modality-invariant module. The former fully leverages modality-specific characteristics by establishing independent branches for each modality. It improves feature discriminability by further enhancing the intra-class compactness and inter-class discrepancy within each modality. The latter is designed with a cross-modality feature distribution consistency loss based on the Gaussian distribution assumption. It significantly alleviates the modality discrepancies by effectively and directly aligning the feature distribution in the unified feature space. As a result, the proposed framework can learn modality-invariant features with enhancing discriminability in each modality. Extensive experimental results on SYSU-MM01 and RegDB demonstrate the effectiveness of our method.
WOS关键词RETRIEVAL ; MODEL
资助项目National Natural Science Foundation of China[2021ZD0110400] ; National Key R &D Program of China[61925303] ; National Key R &D Program of China[62206290] ; National Natural Science Foundation of China
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001206027100001
出版者SPRINGER HEIDELBERG
资助机构National Natural Science Foundation of China ; National Key R &D Program of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/58253]  
专题紫东太初大模型研究中心_大模型计算
通讯作者Zhao, Xu
作者单位1.Beijing Inst Technol, Beijing 100081, Peoples R China
2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
3.Beihang Univ, Beijing 100083, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, La,Zhao, Xu,Du, Haohua,et al. Learning enhancing modality-invariant features for visible-infrared person re-identification[J]. INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS,2024:19.
APA Zhang, La,Zhao, Xu,Du, Haohua,Sun, Jian,&Wang, Jinqiao.(2024).Learning enhancing modality-invariant features for visible-infrared person re-identification.INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS,19.
MLA Zhang, La,et al."Learning enhancing modality-invariant features for visible-infrared person re-identification".INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS (2024):19.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。