cs.CVNov 13, 2026

STaG: Human-Annotation-Free Unsupervised Domain Adaptation for Text-Based Person Retrieval

Authors: Ji Yucheng, Bai Yang, Li Yang, Zhou Xinyu, Cao Min

Organizations: School of Computer Science and Technology, Soochow University, Suzhou, China · School of Computer Science, Wuhan University, Wuhan, China

Abstract

Real-world deployment of Text-Based Person Retrieval (TBPR) is bottlenecked by the absence of textual annotations in new domains. Existing Unsupervised Domain Adaptation (UDA-TBPR) methods still assume access to target-domain human-written annotations (albeit unpaired with images), limiting their practicality. We consider a more practical setting: human-annotation-free UDA-TBPR, with labeled image-text data in the source domain and annotation-free, unlabeled images in the target domain. This setting introduces two core challenges: the absence of cross-modal alignment in the target domain, and visual domain shifts from source to target. To tackle these, we propose STaG, a dual-path framework comprising Style-Agnostic Text Alignment (SATA) and Heterogeneous Graph Memory Alignment (HGMA). Specifically, SATA leverages source-domain data to decouple identity-discriminative semantics from machine-generated stylistic artifacts, establishing robust cross-modal alignment for the target domain. Meanwhile, HGMA exploits cross-domain semantic neighborhoods via a memory-based graph to learn domain-invariant visual features. Ultimately, STaG achieves state-of-the-art performance across three benchmarks under this realistic setting.

Figures & tables

Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Generative Retrieval for Unsupervised Text-Based Person Search

    Sep 11, 2026Mang Ye, Yucheng Ji, Yang Bai +4Text-Based Person SearchUnsupervised Learning

  2. Pretrain-then-Adapt: Uncertainty-Aware Test-Time Adaptation for Text-based Person Search

    Apr 7, 2026Jiahao Zhang, Shaofei Huang, Yaxiong Wang +1Text-Based Person SearchTest-Time Adaptation

  3. Rethinking Text-Based Image Retrieval in Specific Domain

    Aug 11, 2026Jingyang Tan, Sheng Yang, Yuanpeng Chen +4Image-Text RetrievalVision-Language Retrieval