Reliable Pseudo-Supervision for Unsupervised Domain Adaptive Person Search
IEEE Transactions on Image Processing · 2026 · 35 · 915-929
DOI: 10.1109/tip.2026.3654373 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Qixian Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program.
Abstract (Originalsprache)
Unsupervised Domain Adaptation (UDA) person search aims to adapt models trained on labeled source data to unlabeled target domains. Existing approaches typically rely on clustering-based proxy learning, but their performance is often undermined by unreliable pseudo-supervision. This unreliability mainly stems from two challenges: (i) spectral shift bias, where low- and high-frequency components behave differently under domain shifts but are rarely considered, degrading feature stability; and (ii) static proxy updates, which make clustering proxies highly sensitive to noise and less adaptable to domain shifts. To address these challenges, we propose the Reliable Pseudo-supervision in UDA Person Search (RPPS) framework. At the feature level, a Dual-branch Wavelet Enhancement Module (DWEM) embedded in the backbone applies discrete wavelet transform (DWT) to decompose features into low- and high-frequency components, followed by differentiated enhancements that improve cross-domain robustness and discriminability. At the proxy level, a Dynamic Confidence-weighted Clustering Proxy (DCCP) employs confidence-guided initialization and a two-stage online-offline update strategy to stabilize proxy optimization and suppress proxy noise. Extensive experiments on the CUHK-SYSU and PRW benchmarks demonstrate that RPPS achieves state-of-the-art performance and strong robustness, underscoring the importance of enhancing pseudo-supervision reliability in UDA person search. Our code is accessible at https://github.com/zqx951102/RPPS.
Förderung
- National Natural Science Foundation of China
- National Key Research and Development Program
Zitieren
APA
Zhang, Q., Miao, D., Zhang, Q., Tan, X., Zhang, H., & Zhao, C. (2026). Reliable Pseudo-Supervision for Unsupervised Domain Adaptive Person Search. IEEE Transactions on Image Processing, 35, 915-929. https://doi.org/10.1109/tip.2026.3654373
Vancouver
Zhang Q, Miao D, Zhang Q, Tan X, Zhang H, Zhao C. Reliable Pseudo-Supervision for Unsupervised Domain Adaptive Person Search. IEEE Transactions on Image Processing. 2026;35:915-929. doi:10.1109/tip.2026.3654373
BibTeX
@article{Zhang2026,
author = {Zhang, Qixian and Miao, Duoqian and Zhang, Qi and Tan, Xuan and Zhang, Hongyun and Zhao, Cairong},
title = {Reliable Pseudo-Supervision for Unsupervised Domain Adaptive Person Search},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {915--929},
doi = {10.1109/tip.2026.3654373}
}
EUVIMED