Visible-Infrared Person Re-Identification via Partially Interactive Collaboration | |
Zheng, Xiangtao1; Chen, Xiumei2,3,4; Lu, Xiaoqiang5 | |
作者部门 | 光谱成像技术研究室 |
2022 | |
发表期刊 | IEEE TRANSACTIONS ON IMAGE PROCESSING |
ISSN | 1057-7149;1941-0042 |
卷号 | 31页码:6951-6963 |
产权排序 | 1 |
摘要 | Visible-infrared person re-identification (VI-ReID) task aims to retrieve the same person between visible and infrared images. VI-ReID is challenging as the images captured by different spectra present large cross-modality discrepancy. Many methods adopt a two-stream network and design additional constraint conditions to extract shared features for different modalities. However, the interaction between the feature extraction processes of different modalities is rarely considered. In this paper, a partially interactive collaboration method is proposed to exploit the complementary information of different modalities to reduce the modality gap for VI-ReID. Specifically, the proposed method is achieved in a partially interactive-shared architecture: collaborative shallow layers and shared deep layers. The collaborative shallow layers consider the interaction between modality-specific features of different modalities, encouraging the feature extraction processes of different modalities constrain each other to enhance feature representations. The shared deep layers further embed the modality-specific features to a common space to endow them the same identity discriminability. To ensure the interactive collaborative learning implement effectively, the conventional loss and collaborative loss are utilized jointly to train the whole network. Extensive experiments on two publicly available VI-ReID datasets verify the superiority of the proposed PIC method. Specifically, the proposed method achieves a rank-1 accuracy of 83.6% and 57.5% on RegDB and SYSU-MM01 datasets, respectively. |
关键词 | Collaboration Feature extraction Training Federated learning Cameras Task analysis Representation learning Person re-identification cross-modality collaborative learning partially interactive-shared |
DOI | 10.1109/TIP.2022.3217697 |
收录类别 | SCI |
语种 | 英语 |
WOS记录号 | WOS:000880642200003 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/96239 |
专题 | 光谱成像技术研究室 |
通讯作者 | Lu, Xiaoqiang |
作者单位 | 1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Key Lab Spectral Imaging Technol CAS, Xian 710119, Peoples R China 2.Xidian Univ, Hangzhou Inst Technol, Hangzhou 311200, Peoples R China 3.Xidian Univ, Sch Comp Sci & Technol, Xian 710071, Peoples R China 4.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian 710119, Peoples R China 5.Qiyuan Lab, Beijing 100095, Peoples R China |
推荐引用方式 GB/T 7714 | Zheng, Xiangtao,Chen, Xiumei,Lu, Xiaoqiang. Visible-Infrared Person Re-Identification via Partially Interactive Collaboration[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2022,31:6951-6963. |
APA | Zheng, Xiangtao,Chen, Xiumei,&Lu, Xiaoqiang.(2022).Visible-Infrared Person Re-Identification via Partially Interactive Collaboration.IEEE TRANSACTIONS ON IMAGE PROCESSING,31,6951-6963. |
MLA | Zheng, Xiangtao,et al."Visible-Infrared Person Re-Identification via Partially Interactive Collaboration".IEEE TRANSACTIONS ON IMAGE PROCESSING 31(2022):6951-6963. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Visible-Infrared Per(2955KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
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。
修改评论