Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.04998 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909726977032192 |
|---|---|
| author | Zhi, Rui Yang, Zhen Zhang, Haiyang |
| author_facet | Zhi, Rui Yang, Zhen Zhang, Haiyang |
| contents | Person re-identification (Re-ID) aims to match person images across different camera views, with occluded Re-ID addressing scenarios where pedestrians are partially visible. While pre-trained vision-language models have shown effectiveness in Re-ID tasks, they face significant challenges in occluded scenarios by focusing on holistic image semantics while neglecting fine-grained attribute information. This limitation becomes particularly evident when dealing with partially occluded pedestrians or when distinguishing between individuals with subtle appearance differences. To address this limitation, we propose Attribute-Guide ReID (AG-ReID), a novel framework that leverages pre-trained models' inherent capabilities to extract fine-grained semantic attributes without additional data or annotations. Our framework operates through a two-stage process: first generating attribute pseudo-labels that capture subtle visual characteristics, then introducing a dual-guidance mechanism that combines holistic and fine-grained attribute information to enhance image feature extraction. Extensive experiments demonstrate that AG-ReID achieves state-of-the-art results on multiple widely-used Re-ID datasets, showing significant improvements in handling occlusions and subtle attribute differences while maintaining competitive performance on standard Re-ID scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04998 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Attribute Guidance With Inherent Pseudo-label For Occluded Person Re-identification Zhi, Rui Yang, Zhen Zhang, Haiyang Computer Vision and Pattern Recognition Person re-identification (Re-ID) aims to match person images across different camera views, with occluded Re-ID addressing scenarios where pedestrians are partially visible. While pre-trained vision-language models have shown effectiveness in Re-ID tasks, they face significant challenges in occluded scenarios by focusing on holistic image semantics while neglecting fine-grained attribute information. This limitation becomes particularly evident when dealing with partially occluded pedestrians or when distinguishing between individuals with subtle appearance differences. To address this limitation, we propose Attribute-Guide ReID (AG-ReID), a novel framework that leverages pre-trained models' inherent capabilities to extract fine-grained semantic attributes without additional data or annotations. Our framework operates through a two-stage process: first generating attribute pseudo-labels that capture subtle visual characteristics, then introducing a dual-guidance mechanism that combines holistic and fine-grained attribute information to enhance image feature extraction. Extensive experiments demonstrate that AG-ReID achieves state-of-the-art results on multiple widely-used Re-ID datasets, showing significant improvements in handling occlusions and subtle attribute differences while maintaining competitive performance on standard Re-ID scenarios. |
| title | Attribute Guidance With Inherent Pseudo-label For Occluded Person Re-identification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.04998 |