Journal
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
Volume -, Issue -, Pages 11813-11822Publisher
IEEE
DOI: 10.1109/ICCV48922.2021.01162
Keywords
-
Funding
- National Science Fund for Distinguished Young Scholars [62025603]
- National Natural Science Foundation of China [62072386, 62072387, 62072389, 62002305, 61772443, 61802324, 61702136]
- Guangdong Basic and Applied Basic Research Foundation [2019B1515120049]
- Fundamental Research Funds for the Central Universities [20720200077, 20720200090, 20720200091]
Ask authors/readers for more resources
The paper proposes an OcclusionAware Mask Network (OAMN) to address occluded person re-identification problems, which includes an attention-guided mask module requiring labeled occlusion data and a novel occlusion augmentation scheme. Experimental results demonstrate the superiority of OAMN over existing techniques on various person re-identification benchmark datasets.
Person Re-Identification (ReID) has achieved remarkable performance along with the deep learning era. However, most approaches carry out ReID only based upon holistic pedestrian regions. In contrast, real-world scenarios involve occluded pedestrians, which provide partial visual appearances and destroy the ReID accuracy. A common strategy is to locate visible body parts by auxiliary model, which however suffers from significant domain gaps and data bias issues. To avoid such problematic models in occluded person ReID, we propose the OcclusionAware Mask Network (OAMN). In particular, we incorporate an attention-guided mask module, which requires guidance from labeled occlusion data. To this end, we propose a novel occlusion augmentation scheme that produces diverse and precisely labeled occlusion for any holistic dataset. The proposed scheme suits real-world scenarios better than existing schemes, which consider only limited types of occlusions. We also offer a novel occlusion unification scheme to tackle ambiguity information at the test phase. The above three components enable existing attention mechanisms to precisely capture body parts regardless of the occlusion. Comprehensive experiments on a variety of person ReID benchmarks demonstrate the superiority of OAMN over state-of-the-arts.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available