ReText：用文本提升基于图像的行人重识别泛化能力

View PDF HTML (experimental)

Abstract:Generalizable image-based person re-identification (Re-ID) aims to recognize individuals across cameras in unseen domains without retraining. While visual features are sensitive to domain shifts, natural language descriptions remain consistent across domains, regardless of lighting changes and other biases. Since well-known multi-camera datasets lack textual descriptions, we update them with captions through a fine-tuned Vision-Language Model (VLM). We propose ReText, a novel method trained with textual supervision to enrich visual features with semantic cues. Besides, inspired by recent findings showing that incorporating single-camera data into training improves generalization, we also adopt this strategy. However, in contrast to such prior works, we exploit not only visual information but also the textual annotations naturally accompanying these samples. Finally, during training, ReText jointly optimizes three tasks: (1) Re-ID, (2) image-text matching, and (3) image reconstruction guided by text. Experiments demonstrate that ReText achieves strong generalization and significantly outperforms state-of-the-art methods on cross-domain Re-ID benchmarks. The expanded multi-camera datasets and VLM weights are publicly available at this https URL.

Comments:	Accepted by WACV 2027
Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:	arXiv:2602.05785 [cs.CV]
	(or arXiv:2602.05785v2 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2602.05785 arXiv-issued DOI via DataCite

Submission history

From: Timur Mamedov [view email]
[v1] Thu, 5 Feb 2026 15:43:31 UTC (1,373 KB)
[v2] Thu, 15 Oct 2026 09:12:09 UTC (13,670 KB)