DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910312741994496 |
|---|---|
| author | Dou, Shuguang Jiang, Xiangyang Tu, Yuanpeng Gao, Junyao Qu, Zefan Zhao, Qingsong Zhao, Cairong |
| author_facet | Dou, Shuguang Jiang, Xiangyang Tu, Yuanpeng Gao, Junyao Qu, Zefan Zhao, Qingsong Zhao, Cairong |
| contents | The paper introduces the Decouple Re-identificatiOn and human Parsing (DROP) method for occluded person re-identification (ReID). Unlike mainstream approaches using global features for simultaneous multi-task learning of ReID and human parsing, or relying on semantic information for attention guidance, DROP argues that the inferior performance of the former is due to distinct granularity requirements for ReID and human parsing features. ReID focuses on instance part-level differences between pedestrian parts, while human parsing centers on semantic spatial context, reflecting the internal structure of the human body. To address this, DROP decouples features for ReID and human parsing, proposing detail-preserving upsampling to combine varying resolution feature maps. Parsing-specific features for human parsing are decoupled, and human position information is exclusively added to the human parsing branch. In the ReID branch, a part-aware compactness loss is introduced to enhance instance-level part differences. Experimental results highlight the efficacy of DROP, especially achieving a Rank-1 accuracy of 76.8% on Occluded-Duke, surpassing two mainstream methods. The codebase is accessible at https://github.com/shuguang-52/DROP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_18032 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identification Dou, Shuguang Jiang, Xiangyang Tu, Yuanpeng Gao, Junyao Qu, Zefan Zhao, Qingsong Zhao, Cairong Computer Vision and Pattern Recognition The paper introduces the Decouple Re-identificatiOn and human Parsing (DROP) method for occluded person re-identification (ReID). Unlike mainstream approaches using global features for simultaneous multi-task learning of ReID and human parsing, or relying on semantic information for attention guidance, DROP argues that the inferior performance of the former is due to distinct granularity requirements for ReID and human parsing features. ReID focuses on instance part-level differences between pedestrian parts, while human parsing centers on semantic spatial context, reflecting the internal structure of the human body. To address this, DROP decouples features for ReID and human parsing, proposing detail-preserving upsampling to combine varying resolution feature maps. Parsing-specific features for human parsing are decoupled, and human position information is exclusively added to the human parsing branch. In the ReID branch, a part-aware compactness loss is introduced to enhance instance-level part differences. Experimental results highlight the efficacy of DROP, especially achieving a Rank-1 accuracy of 76.8% on Occluded-Duke, surpassing two mainstream methods. The codebase is accessible at https://github.com/shuguang-52/DROP. |
| title | DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.18032 |