Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2302.04607 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914631244578816 |
|---|---|
| author | Wang, Jiabei Pang, Yanwei Cao, Jiale Sun, Hanqing Shao, Zhuang Li, Xuelong |
| author_facet | Wang, Jiabei Pang, Yanwei Cao, Jiale Sun, Hanqing Shao, Zhuang Li, Xuelong |
| contents | Weakly supervised person search aims to perform joint pedestrian detection and re-identification (re-id) with only person bounding-box annotations. Recently, the idea of contrastive learning is initially applied to weakly supervised person search, where two common contrast strategies are memory-based contrast and intra-image contrast. We argue that current intra-image contrast is shallow, which suffers from spatial-level and occlusion-level variance. In this paper, we present a novel deep intra-image contrastive learning using a Siamese network. Two key modules are spatial-invariant contrast (SIC) and occlusion-invariant contrast (OIC). SIC performs many-to-one contrasts between two branches of Siamese network and dense prediction contrasts in one branch of Siamese network. With these many-to-one and dense contrasts, SIC tends to learn discriminative scale-invariant and location-invariant features to solve spatial-level variance. OIC enhances feature consistency with the masking strategy to learn occlusion-invariant features. Extensive experiments are performed on two person search datasets CUHK-SYSU and PRW, respectively. Our method achieves a state-of-the-art performance among weakly supervised one-step person search approaches. We hope that our simple intra-image contrastive learning can provide more paradigms on weakly supervised person search. The source code is available at \url{https://github.com/jiabeiwangTJU/DICL}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_04607 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Search Wang, Jiabei Pang, Yanwei Cao, Jiale Sun, Hanqing Shao, Zhuang Li, Xuelong Computer Vision and Pattern Recognition Weakly supervised person search aims to perform joint pedestrian detection and re-identification (re-id) with only person bounding-box annotations. Recently, the idea of contrastive learning is initially applied to weakly supervised person search, where two common contrast strategies are memory-based contrast and intra-image contrast. We argue that current intra-image contrast is shallow, which suffers from spatial-level and occlusion-level variance. In this paper, we present a novel deep intra-image contrastive learning using a Siamese network. Two key modules are spatial-invariant contrast (SIC) and occlusion-invariant contrast (OIC). SIC performs many-to-one contrasts between two branches of Siamese network and dense prediction contrasts in one branch of Siamese network. With these many-to-one and dense contrasts, SIC tends to learn discriminative scale-invariant and location-invariant features to solve spatial-level variance. OIC enhances feature consistency with the masking strategy to learn occlusion-invariant features. Extensive experiments are performed on two person search datasets CUHK-SYSU and PRW, respectively. Our method achieves a state-of-the-art performance among weakly supervised one-step person search approaches. We hope that our simple intra-image contrastive learning can provide more paradigms on weakly supervised person search. The source code is available at \url{https://github.com/jiabeiwangTJU/DICL}. |
| title | Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Search |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2302.04607 |