VLUReID: Exploiting Vision-Language Knowledge for Unsupervised Person Re-Identification

Dongmei Zhang, Ray Zhang, Fan Yang, Yuan Li, Huizhu Jia, Xiaodong Xie, Shanghang ZhangICME 2024 · OpenReview

Abstract

The superior performances of pre-trained vision-language models on various downstream tasks demonstrate the effectiveness of integrating cross-modal vision-language knowledge into visual tasks. However, this knowledge is hardly used for visual-based person re-identification (re-ID) because the datasets lack textual descriptions. Existing efforts require manual annotations for training, which can be time-consuming. We propose VLUReID, a framework that improves visual-based person re-ID using vision-language knowledge without requiring manual annotations from datasets. Specifically, the Vision-to-Text Association (VTA) module uses designed textual prompts to prompt the vision-language model in generating pseudo-semantic labels for visual inputs. Subsequently, within the Dual-Branch Asymmetric Training (DBAT) module, we propose an asymmetric training strategy to extract cross-modal knowledge from pseudo-semantic labels and integrate it into the person re-ID model. The experimental results on two widely-used benchmarks for unsupervised video-based person re-ID demonstrate the effectiveness of our framework.
BibTeX
@inproceedings{zhang2024vlureid,
  author = {Dongmei Zhang and Ray Zhang and Fan Yang and Yuan Li and Huizhu Jia and Xiaodong Xie and Shanghang Zhang},
  title = {{VLUReID: Exploiting Vision-Language Knowledge for Unsupervised Person Re-Identification}},
  booktitle = {ICME},
  year = {2024},
  url = {https://openreview.net/forum?id=K6Zi81EnTt},
}

Loading related content...

Figure