Multi-Scale Body-Part Mask Guided Attention for Person Re-identification
This work addresses person re-identification for surveillance and security applications, representing an incremental improvement over existing methods.
The paper tackles the challenge of person re-identification by proposing a multi-scale body-part mask guided attention network (MMGA) to reduce negative influences like pose variation and background clutter, achieving state-of-the-art results such as 95.0% rank-1 accuracy on the Market1501 dataset.
Person re-identification becomes a more and more important task due to its wide applications. In practice, person re-identification still remains challenging due to the variation of person pose, different lighting, occlusion, misalignment, background clutter, etc. In this paper, we propose a multi-scale body-part mask guided attention network (MMGA), which jointly learns whole-body and part body attention to help extract global and local features simultaneously. In MMGA, body-part masks are used to guide the training of corresponding attention. Experiments show that our proposed method can reduce the negative influence of variation of person pose, misalignment and background clutter. Our method achieves rank-1/mAP of 95.0%/87.2% on the Market1501 dataset, 89.5%/78.1% on the DukeMTMC-reID dataset, outperforming current state-of-the-art methods.