Abstract
Person re-identification aims to robustly measure similarities between person images. The significant variation of person poses and viewing angles challenges for accurate person re-identification. The spatial layout and correspondences between query person images are vital information for tackling this problem but are ignored by most state-of-the-art methods. In this paper, we propose a novel Kronecker Product Matching module to match feature maps of different persons in an end-to-end trainable deep neural network. A novel feature soft warping scheme is designed for aligning the feature maps based on matching results, which is shown to be crucial for achieving superior accuracy. The multi-scale features based on hourglass-like networks and self-residual attention are also exploited to further boost the re-identification performance. The proposed approach outperforms state-of-the-art methods on the Market-1501, CUHK03, and DukeMTMC datasets, which demonstrates the effectiveness and generalization ability of our proposed approach.
Abstract (translated)
人员重新识别旨在稳健地测量人物图像之间的相似性。人体姿势和视角的显着变化对于准确的人重新识别提出了挑战。查询人图像之间的空间布局和对应关系是解决此问题的重要信息,但大多数最先进的方法都忽略了这些信息。在本文中,我们提出了一种新颖的Kronecker产品匹配模块,以匹配端到端可训练深度神经网络中不同人员的特征图。一种新颖的特征软翘曲方案被设计用于基于匹配结果对准特征图,这被证明对于实现高精度是至关重要的。基于类沙漏网络和自残留注意力的多尺度特征也被用于进一步提高重新识别性能。所提出的方法优于Market-1501,CUHK03和DukeMTMC数据集上的最新方法,这些方法证明了我们提出的方法的有效性和泛化能力。
URL
https://arxiv.org/abs/1807.11182