FCL: Pedestrian Re-Identification Algorithm Based on Feature Fusion Contrastive Learning
-
Published:2024-06-17
Issue:12
Volume:13
Page:2368
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Li Yuangang1ORCID, Zhang Yuhan2, Gao Yunlong2ORCID, Xu Bo3, Liu Xinyue2
Affiliation:
1. Faculty of Business Information, Shanghai Business School, Shanghai 200235, China 2. School of Software, Dalian University of Technology, Dalian 116024, China 3. School of Computer Science, Dalian University of Technology, Dalian 116024, China
Abstract
Pedestrian re-identification leverages computer vision technology to achieve cross-camera matching of pedestrians; it has recently led to significant progress and presents numerous practical applications. However, current algorithms face the following challenges: (1) most of the methods are supervised, heavily relying on specific datasets, and lacking robust generalization capabilities; (2) it is hard to extract features because the elongated and narrow shape of pedestrian images introduces uneven feature distributions; (3) the substantial imbalance between positive and negative samples. To address these challenges, we introduce a novel pedestrian re-identification unsupervised algorithm called Feature Fusion Contrastive Learning (FCL) to extract more effective features. Specifically, we employ circular pooling to merge network features across different levels for pedestrian re-identification to improve robust generalization capability. Furthermore, we propose a feature fusion pooling method, which facilitates a more efficient distribution of feature representations across pedestrian images. Finally, we introduce FocalLoss to compute the clustering-level loss, mitigating the imbalance between positive and negative samples. Through extensive experiments conducted on three prominent datasets, our proposed method demonstrates promising performance, with an average 3.8% improvement in FCL’s mAP indicators compared to baseline results.
Funder
Liaoning Provincial Social Science Planning Fund
Reference43 articles.
1. Li, Y., He, J., Zhang, T., Liu, X., Zhang, Y., and Wu, F. (2021, January 20–25). Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA. 2. Chen, X., Fu, C., Zhao, Y., Zheng, F., Song, J., Ji, R., and Yang, Y. (2020, January 13–19). Salience-Guided Cascaded Suppression Network for Person Re-Identification. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA. 3. Deep learning-based person re-identification methods: A survey and outlook of recent works;Ming;Image Vis. Comput.,2022 4. Chen, Y., Zhu, X., and Gong, S. (November, January 27). Instance-Guided Context Rendering for Cross-Domain Person Re-Identification. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea. 5. Wei, L., Zhang, S., Gao, W., and Tian, Q. (2018, January 18–23). Person Transfer GAN to Bridge Domain Gap for Person Re-Identification. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|