Instance-Guided Scene Adaptation for Unsupervised Person Search

Linfeng Qi; Huibing Wang; Jinjia Peng; Xianping Fu; Jiqing Zhang

AAAI 2026technical0 citations

Instance-Guided Scene Adaptation for Unsupervised Person Search

Linfeng Qi, Huibing Wang, Jinjia Peng, Xianping Fu, Jiqing Zhang

Abstract

Unsupervised Domain Adaptation (UDA) is a challenging task in person search. It adapts a well-trained model from a labeled source domain to an unlabeled target domain for privacy and efficiency. Currently, most of the state-of-the-art UDA person search methods adopt multi-scale feature alignment techniques to learn domain-invariant representations. However, person search is a multi-granularity task, and such an indiscriminate method of bridging the differences between domains misleads the identity learning process, which significantly limits the model

BibTeX

@inproceedings{aaai2026_instanceguidedsc,
  title = {Instance-Guided Scene Adaptation for Unsupervised Person Search},
  author = {Linfeng Qi and Huibing Wang and Jinjia Peng and Xianping Fu and Jiqing Zhang},
  booktitle = {AAAI 2026},
  year = {2026}
}