Privacy-Preserving Replay and Adaptive Relation Distillation for Camera Incremental Person Re-Identification

Zexian Yang, Dayan Wu, Wanqian Zhang, Jingzi Gu, Zheng Lin, Weiping WangICME 2024 · OpenReview

Abstract

Traditional person re-identification (ReID) methods trained on static data are ill-suited to real-world dynamic surveillance systems. Recently, a more desirable setting "Camera Incremental Person ReID (CIPR)", has been proposed to continually adapt to new cameras and accumulate knowledge. However, prior work on relation distillation heavily constrains intra-class relations for all identities, while under-exploring the credibility of different identities in knowledge transfer. Besides, their rehearsal-free setting sidesteps privacy concerns but compromises performance. In this paper, we present a novel framework, P 2 -ARD, designed specifically for CIPR. Firstly, we propose an innovative Adaptive Relation Distillation loss that automatically selects more crucial identities for distillation. Additionally, we introduce the privacy-preserving replay scheme to effectively retain semantic information while ensuring the privacy of the identity. Finally, we incorporate a cycle-consistent correlation method to address the class overlap issue in CIPR. Extensive experiments demonstrate our method outperforming the state-of-the-art.
BibTeX
@inproceedings{yang2024privacy,
  author = {Zexian Yang and Dayan Wu and Wanqian Zhang and Jingzi Gu and Zheng Lin and Weiping Wang},
  title = {{Privacy-Preserving Replay and Adaptive Relation Distillation for Camera Incremental Person Re-Identification}},
  booktitle = {ICME},
  year = {2024},
  url = {https://openreview.net/forum?id=G8hrn5KaRy},
}

Loading related content...

Figure