EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust Fine-Grained Learning for Cloth-Changing Person Re-Identification

Qingze Yin, Guodong Ding, Tongpo Zhang, Yumei Gong

Mathematics · 27.01.2025 · 13 (3) · 429

DOI: 10.3390/math13030429 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 27.01.2025. Verfasst von Qingze Yin und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai Polytechnic University OF FUNDER, Shanghai Polytechnic University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cloth-changing Person Re-Identification (CC-ReID) poses a significant challenge in tracking pedestrians across cameras while accounting for changes in clothing appearance. Despite recent progress in CC-ReID, existing methods predominantly focus on learning the unique biological features of pedestrians, often overlooking constraints that promote the learning of cloth-agnostic features. Addressing this limitation, we propose a Robust Fine-grained Learning Network (RFLNet) to effectively learn robust cloth-agnostic features by leveraging fine-grained semantic constraints. Specifically, we introduce a four-body-part attention module to enhance the learning of detailed pedestrian semantic features. To further strengthen the model’s robustness to clothing variations, we employ a random erasing algorithm, encouraging the network to concentrate on cloth-irrelevant attributes. Additionally, we design a fine-grained semantic loss to guide the model in learning identity-related, detailed semantic features, thereby improving its focus on cloth-agnostic regions. Comprehensive experiments on widely used CC-ReID benchmarks demonstrate the effectiveness of RFLNet. Our method achieves state-of-the-art performance, including a 0.7% increase in mAP on PRCC and a 1.6% improvement in rank-1 accuracy on DeepChange.

Förderung

  • Shanghai Polytechnic University OF FUNDER
  • Shanghai Polytechnic University

Zitieren

APA

Yin, Q., Ding, G., Zhang, T., & Gong, Y. (2025). Robust Fine-Grained Learning for Cloth-Changing Person Re-Identification. Mathematics, 13(3), 429. https://doi.org/10.3390/math13030429

Vancouver

Yin Q, Ding G, Zhang T, Gong Y. Robust Fine-Grained Learning for Cloth-Changing Person Re-Identification. Mathematics. 2025;13(3):429. doi:10.3390/math13030429

BibTeX
@article{Yin2025,
  author = {Yin, Qingze and Ding, Guodong and Zhang, Tongpo and Gong, Yumei},
  title = {Robust Fine-Grained Learning for Cloth-Changing Person Re-Identification},
  journal = {Mathematics},
  year = {2025},
  volume = {13},
  number = {3},
  pages = {429},
  doi = {10.3390/math13030429}
}
Kostenlos starten →