Abstract
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.
Abstract (translated)
人的再识别由于其广泛的应用而成为一项越来越重要的任务。在实践中,由于人体姿态的变化、不同的光照、遮挡、错位、背景杂波等因素,使得人的再识别仍然具有挑战性,本文提出了一种多尺度的人体部分掩模引导注意力网络(MMGA),它可以联合学习全身和部分身体的注意力,帮助提取全局和局部的注意力。同时食用。在MMGA中,身体部位的面具被用来指导相应注意力的训练。实验表明,该方法能有效地降低人的姿态变化、失调和背景杂波的影响。我们的方法在市场1501数据集上实现了95.0%/87.2%的秩1/映射,在Dukemtmc REID数据集上实现了89.5%/78.1%,优于当前最先进的方法。
URL
https://arxiv.org/abs/1904.11041