EUVIMEDEUVIMED entdecken
Crossref

Heterogeneous Feature Re-Sampling for Balanced Pedestrian Attribute Recognition

Yibo Zhou, Bo Li, Hai-Miao Hu, Xiaokang Zhang, Dongping Zhang, Hanzi Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-04 · 47 (4) · 2706-2722

DOI: 10.1109/tpami.2025.3526930 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-04. Verfasst von Yibo Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 100 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In pedestrian attribute recognition (PAR), the loose umbrella term 'attribute' ranges from human soft-biometrics to wearing accessory, and even extending to various subjective body descriptors. As a result, the vast coverage of 'attributes' implies that, instead of being over-specialized to limited attributes with exclusive characteristic, PAR should be approached from a much fundamental perspective. To this end, given that most attributes are greatly under-represented in real-world datasets, we simply distill PAR into a visual task of multi-label recognition under significant data imbalance. Accordingly, we introduce feature re-sampled detached learning (FRDL) to decouple label-balanced learning from the curse of attributes co-occurrence. Specifically, FRDL is able to balance the sampling distribution of an attribute without biasing the label prior of co-occurring others. As a complementary method, we also propose gradient-oriented augment translating (GOAT) to alleviate the feature noise and semantics imbalance aggravated in FRDL. Integrated in a highly unified framework, FRDL and GOAT substantially refresh the state-of-the-art performance on various realistic benchmarks, while maintaining a minimal computational budget. Further analytical discussion and experimental evidence corroborate the veracity of our advancement: this is the first work that establishes labels-independent and impartial balanced learning for PAR.

Zitieren

APA

Zhou, Y., Li, B., Hu, H. M., Zhang, X., Zhang, D., & Wang, H. (2025). Heterogeneous Feature Re-Sampling for Balanced Pedestrian Attribute Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(4), 2706-2722. https://doi.org/10.1109/tpami.2025.3526930

Vancouver

Zhou Y, Li B, Hu HM, Zhang X, Zhang D, Wang H. Heterogeneous Feature Re-Sampling for Balanced Pedestrian Attribute Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(4):2706-2722. doi:10.1109/tpami.2025.3526930

BibTeX
@article{Zhou2025,
  author = {Zhou, Yibo and Li, Bo and Hu, Hai-Miao and Zhang, Xiaokang and Zhang, Dongping and Wang, Hanzi},
  title = {Heterogeneous Feature Re-Sampling for Balanced Pedestrian Attribute Recognition},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {4},
  pages = {2706--2722},
  doi = {10.1109/tpami.2025.3526930}
}
Kostenlos starten →