EUVIMEDEUVIMED entdecken
Crossref

Prototype-Guided Attention Distillation for Discriminative Person Search

Hanjae Kim, Jiyoung Lee, Kwanghoon Sohn

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-01 · 47 (1) · 99-115

DOI: 10.1109/tpami.2024.3461778 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-01. Verfasst von Hanjae Kim und 2 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 121 Literaturangaben. Gefördert von: National Research Foundation of Korea, Korea government, Yonsei Signature Research Cluster Program of 2024.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Person search aims to localize a person of interest in a large image gallery captured by multiple, non-overlapping cameras. Prevalent unified methods have suffered from (1) noisy proposals with mis-detection and occlusion, and (2) large appearance variation within a class, which deteriorates the prototype-based metric learning. To address these problems, we introduce a Prototype-guided Attention Distillation, shortly PAD, which exploits a prototype (a typical representation of an identity) as a guidance to the attention module to consistently highlight identity-inherent regions across different poses. To utilize the knowledge encoded in prototypes for matching unseen IDs, PAD conducts attention distillation to guide student Re-ID queries by deeply mimicking attention maps from the prototype query. Additionally, to address large intra-class variation induced by pose or camera views, we extend PAD with multiple part prototypes representing consistent local regions across different instances. Furthermore, we exploit an adaptive momentum strategy for robust attention distillation in PAD to update more distinct prototypes. Extensive experiments conducted on CUHK-SYSU and PRW demonstrate the effectiveness of PAD, showcasing state-of-the-art performance. Moreover, our distilled attention surprisingly highlights distinguished multiple regions for person search.

Förderung

  • National Research Foundation of Korea
  • Korea government
  • Yonsei Signature Research Cluster Program of 2024

Zitieren

APA

Kim, H., Lee, J., & Sohn, K. (2025). Prototype-Guided Attention Distillation for Discriminative Person Search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(1), 99-115. https://doi.org/10.1109/tpami.2024.3461778

Vancouver

Kim H, Lee J, Sohn K. Prototype-Guided Attention Distillation for Discriminative Person Search. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(1):99-115. doi:10.1109/tpami.2024.3461778

BibTeX
@article{Kim2025,
  author = {Kim, Hanjae and Lee, Jiyoung and Sohn, Kwanghoon},
  title = {Prototype-Guided Attention Distillation for Discriminative Person Search},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {1},
  pages = {99--115},
  doi = {10.1109/tpami.2024.3461778}
}
Kostenlos starten →