Parsing-based View-aware Embedding Network for Vehicle Re-Identification

• DOI: 10.48550/arxiv.2004.05021
• Publication Date: 2020-01-01
• Authors: Dechao Meng; Liang Li; Xuejing Liu; Yadong Li; Shijie Yang; Zheng-Jun Zha; Xingyu Gao; Shuhui Wang; Qingming Huang
• Keywords: Discriminative model; Pooling; Margin (machine learning); Representation; Identification; Feature (linguistics)

Vehicle Re-Identification is to find images of the same vehicle from various views in cross-camera scenario. The main challenges this task are large intra-instance distance caused by different and subtle inter-instance discrepancy similar vehicles. In paper, we propose a parsing-based view-aware embedding network (PVEN) achieve feature alignment enhancement for ReID. First, introduce parsing parse into four views, then align features mask average pooling. Such provides fine-grained representation vehicle. Second, order enhance features, design common-visible attention focus on common visible which not only shortens among intra-instances, but also enlarges inter-instances. PVEN helps capture stable discriminative information under views. experiments conducted three datasets show that our model outperforms state-of-the-art methods margin.