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

被引:1
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 36 条
[1]   Neural Feature Search for RGB-Infrared Person Re-Identification [J].
Chen, Yehansen ;
Wan, Lin ;
Li, Zhihang ;
Jing, Qianyan ;
Sun, Zongyuan .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :587-597
[2]   Learning Modality-Specific Representations for Visible-Infrared Person Re-Identification [J].
Feng, Zhanxiang ;
Lai, Jianhuang ;
Xie, Xiaohua .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 :579-590
[3]   CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification [J].
Fu, Chaoyou ;
Hu, Yibo ;
Wu, Xiang ;
Shi, Hailin ;
Mei, Tao ;
He, Ran .
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :11803-11812
[4]   Person Re-Identification Using Deep Modeling of Temporally Correlated Inertial Motion Patterns [J].
Gohar, Imad ;
Riaz, Qaiser ;
Shahzad, Muhammad ;
Hashmi, Muhammad Zeeshan Ul Hasnain ;
Tahir, Hasan ;
Ul Haq, Muhammad Ehsan .
SENSORS, 2020, 20 (03)
[5]   Cross-Modality Person Re-Identification via Modality Confusion and Center Aggregation [J].
Hao, Xin ;
Zhao, Sanyuan ;
Ye, Mang ;
Shen, Jianbing .
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :16383-16392
[6]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[7]   Coordinate Attention for Efficient Mobile Network Design [J].
Hou, Qibin ;
Zhou, Daquan ;
Feng, Jiashi .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :13708-13717
[8]   Interaction-and-Aggregation Network for Person Re-identification [J].
Hou, Ruibing ;
Ma, Bingpeng ;
Chang, Hong ;
Gu, Xinqian ;
Shan, Shiguang ;
Chen, Xilin .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :9309-9318
[9]  
Li DG, 2020, AAAI CONF ARTIF INTE, V34, P4610
[10]   Combined Depth Space based Architecture Search For Person Re-identification [J].
Li, Hanjun ;
Wu, Gaojie ;
Zheng, Wei-Shi .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :6725-6734