Progressive Discriminative Feature Learning for Visible-Infrared Person Re-Identification

被引:0
|
作者
Zhou, Feng [1 ]
Cheng, Zhuxuan [2 ]
Yang, Haitao [1 ]
Song, Yifeng [2 ]
Fu, Shengpeng [2 ]
机构
[1] Hunan Police Acad, Dept Criminal Ivest, Changsha 410138, Peoples R China
[2] Chinese Acad Sci, Shenyang Inst Automat, Shenyang 110016, Peoples R China
基金
中国国家自然科学基金;
关键词
visible-infrared person re-identification; cross-modality; deep learning; instance normalization;
D O I
10.3390/electronics13142825
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The visible-infrared person re-identification (VI-ReID) task aims to retrieve the same pedestrian between visible and infrared images. VI-ReID is a challenging task due to the huge modality discrepancy and complex intra-modality variations. Existing works mainly complete the modality alignment at one stage. However, aligning modalities at different stages has positive effects on the intra-class and inter-class distances of cross-modality features, which are often ignored. Moreover, discriminative features with identity information may be corrupted in the processing of modality alignment, further degrading the performance of person re-identification. In this paper, we propose a progressive discriminative feature learning (PDFL) network that adopts different alignment strategies at different stages to alleviate the discrepancy and learn discriminative features progressively. Specifically, we first design an adaptive cross fusion module (ACFM) to learn the identity-relevant features via modality alignment with channel-level attention. For well preserving identity information, we propose a dual-attention-guided instance normalization module (DINM), which can well guide instance normalization to align two modalities into a unified feature space through channel and spatial information embedding. Finally, we generate multiple part features of a person to mine subtle differences. Multi-loss optimization is imposed during the training process for more effective learning supervision. Extensive experiments on the public datasets of SYSU-MM01 and RegDB validate that our proposed method performs favorably against most state-of-the-art methods.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] Diverse-Feature Collaborative Progressive Learning for Visible-Infrared Person Re-Identification
    Chan, Sixian
    Meng, Weihao
    Bai, Cong
    Hu, Jie
    Chen, Shenyong
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2024, 20 (05) : 7754 - 7763
  • [2] Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification
    Ren, Kaijie
    Zhang, Lei
    2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2024, 2024, : 393 - 402
  • [3] Stronger Heterogeneous Feature Learning for Visible-Infrared Person Re-Identification
    Hao Wang
    Xiaojun Bi
    Changdong Yu
    Neural Processing Letters, 56
  • [4] Stronger Heterogeneous Feature Learning for Visible-Infrared Person Re-Identification
    Wang, Hao
    Bi, Xiaojun
    Yu, Changdong
    NEURAL PROCESSING LETTERS, 2024, 56 (02)
  • [5] Visible-Infrared Person Re-Identification Via Feature Constrained Learning
    Zhang Jing
    Chen Guangfeng
    LASER & OPTOELECTRONICS PROGRESS, 2024, 61 (12)
  • [6] Progressive discrepancy elimination for visible-infrared person re-identification
    Zhang, Guoqing
    Wang, Zhun Zhun
    Wang, Hairui
    Zhou, Jieqiong
    Zheng, Yuhui
    NEUROCOMPUTING, 2024, 607
  • [7] Multi-dimensional feature learning for visible-infrared person re-identification
    Yang, Zhenzhen
    Wu, Xinyi
    Yang, Yongpeng
    BIG DATA RESEARCH, 2025, 40
  • [8] Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification
    Feng, Jiawei
    Wu, Ancong
    Zhen, Wei-Shi
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 22752 - 22761
  • [9] Unbiased Feature Learning with Causal Intervention for Visible-Infrared Person Re-Identification
    Yuan, Bo wen
    Lu, Jiahao
    You, Sisi
    Bao, Bing-kun
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2024, 20 (10)
  • [10] Learning dual attention enhancement feature for visible-infrared person re-identification
    Zhang, Guoqing
    Zhang, Yinyin
    Zhang, Hongwei
    Chen, Yuhao
    Zheng, Yuhui
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2024, 99