Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913239008280576 |
|---|---|
| author | Xia, Jiaer Tan, Lei Dai, Pingyang Zhao, Mingbo Wu, Yongjian Cao, Liujuan |
| author_facet | Xia, Jiaer Tan, Lei Dai, Pingyang Zhao, Mingbo Wu, Yongjian Cao, Liujuan |
| contents | Occluded person re-identification (Re-ID) aims to address the potential occlusion problem when matching occluded or holistic pedestrians from different camera views. Many methods use the background as artificial occlusion and rely on attention networks to exclude noisy interference. However, the significant discrepancy between simple background occlusion and realistic occlusion can negatively impact the generalization of the network. To address this issue, we propose a novel transformer-based Attention Disturbance and Dual-Path Constraint Network (ADP) to enhance the generalization of attention networks. Firstly, to imitate real-world obstacles, we introduce an Attention Disturbance Mask (ADM) module that generates an offensive noise, which can distract attention like a realistic occluder, as a more complex form of occlusion. Secondly, to fully exploit these complex occluded images, we develop a Dual-Path Constraint Module (DPC) that can obtain preferable supervision information from holistic images through dual-path interaction. With our proposed method, the network can effectively circumvent a wide variety of occlusions using the basic ViT baseline. Comprehensive experimental evaluations conducted on person re-ID benchmarks demonstrate the superiority of ADP over state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_10976 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification Xia, Jiaer Tan, Lei Dai, Pingyang Zhao, Mingbo Wu, Yongjian Cao, Liujuan Computer Vision and Pattern Recognition Occluded person re-identification (Re-ID) aims to address the potential occlusion problem when matching occluded or holistic pedestrians from different camera views. Many methods use the background as artificial occlusion and rely on attention networks to exclude noisy interference. However, the significant discrepancy between simple background occlusion and realistic occlusion can negatively impact the generalization of the network. To address this issue, we propose a novel transformer-based Attention Disturbance and Dual-Path Constraint Network (ADP) to enhance the generalization of attention networks. Firstly, to imitate real-world obstacles, we introduce an Attention Disturbance Mask (ADM) module that generates an offensive noise, which can distract attention like a realistic occluder, as a more complex form of occlusion. Secondly, to fully exploit these complex occluded images, we develop a Dual-Path Constraint Module (DPC) that can obtain preferable supervision information from holistic images through dual-path interaction. With our proposed method, the network can effectively circumvent a wide variety of occlusions using the basic ViT baseline. Comprehensive experimental evaluations conducted on person re-ID benchmarks demonstrate the superiority of ADP over state-of-the-art methods. |
| title | Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2303.10976 |