Looking Twice for Partial Clues: Weakly-supervised Part-Mentored Attention Network for Vehicle Re-Identification

Abstract

Vehicle re-identification (Re-ID) is to retrieve images of the same vehicle across different cameras. Two key challenges lie in the subtle inter-instance discrepancy caused by nearduplicate identities and the large intra-instance variance caused by different views. Since the holistic appearance suffers from viewpoint variation and distortion, part-level feature learning has been introduced to enhance vehicle description. However, existing approaches to localize and amplify significant parts often fail to handle spatial misalignment as well as occlusion and require expensive annotations. In this paper, we propose a weakly-supervised Part-Mentored Attention Network (PMANet) consisting of a Part Attention Network (PANet) for vehicle part localization with self-attention and a Part-Mentored Network (PMNet) for mentoring the global and local feature aggregation. Firstly, PANet is introduced to predict a foreground mask and pinpoint K prominent vehicle parts only with a weak identity supervision. Secondly, we propose a PMNet to learn global and part-level features with multi-scale spatial and channel attention and aggregate them in K main-partial tasks via part transfer. Like humans who first differentiate objects with general information and then observe salient parts for more detailed clues, PANet and PMNet construct a two-stage attention structure to perform a coarse-to-fine search among identities. Finally, we address this Re-ID issue as a multi-task problem, including global feature learning, identity classification, and part transfer. We adopt Homoscedastic Uncertainty to learn the optimal weighing of different losses. Comprehensive experiments are conducted on two benchmark datasets. Our approach outperforms recent stateof-the-art methods by averagely 2.63% in CMC@1 on VehicleID and 2.2% in mAP on VeRi776. Moreover, Experimental results on occluded test sets demonstrate that PMANet has a good generalization ability.