Joint multi-scale discrimination and region segmentation for person re-ID

摘要

Most existing person re-identification methods are mainly based on human part partition with horizontal stripes or human body semantic segmentation. In this paper, we propose a method called MDRS (Multiscale Discriminative network with Region Segmentation) to integrate multi-scale discriminative feature learning, horizontal stripe partition and semantic segmentation in a single framework, in which multiscale horizontal stripe partition and usage of both global and local features make the framework be robust to human pose variation, occlusion and background clutter, and semantic segmentation boosts the performance of person identification via shared multi-scale feature extraction. MDRS is trained end-to-end with a multi-task learning strategy that considers three tasks simultaneously: person identification, triplet prediction and pixel-wise semantic segmentation. Comprehensive experiments confirm that our approach exceeds many methods and robustly achieves excellent performances on mainstream evaluation datasets including Market-1501, DukeMTMC-reid and CUHK03. (C) 2020 Elsevier B.V. All rights reserved.