A Novel Dual Mixing Attention Network for UAV-Based Vehicle Re-Identification

Abstract

Vehicle re-identification research under surveillance cameras has yielded impressive results. However, the challenge of unmanned aerial vehicle (UAV)-based vehicle re-identification (ReID) presents a high degree of flexibility, mainly due to complicated shooting angles, occlusions, low discrimination of top–down features, and significant changes in vehicle scales. To address this, we propose a novel dual mixing attention network (DMANet) to extract discriminative features robust to variations in viewpoint. Specifically, we first present a plug-and-play dual mixing attention module (DMAM) to capture pixel-level pairwise relationships and channel dependencies, where DMAM is composed of spatial mixing attention (SMA) and channel mixing attention (CMA). First, the original feature is divided according to the spatial and channel dimensions to obtain multiple subspaces. Then, a learnable weight is applied to capture the dependencies between local features in the mixture space. Finally, the features extracted from all subspaces are aggregated to promote their comprehensive feature interaction. In addition, DMAM can be easily plugged into any depth of the backbone network to improve vehicle recognition. The experimental results show that the proposed structure performs better than the representative method in the UAV-based vehicle ReID. Our code and models will be published publicly.