Region-guided spatial feature aggregation network for vehicle re-identification

Abstract

In the context of the advancement of smart city management, re-identification technology has emerged as an area of particular interest and research in the field of artificial intelligence, especially vehicle re-identification (re-ID), which aims to identify target vehicles in multiple non-overlapping fields of view. Most existing methods rely on fine-grained cues in the salient regions. Although impressive results have been achieved, these methods typically require additional auxiliary networks to localize the salient regions containing fine-grained cues. Meanwhile, changes in state such as illumination, viewpoint and occlusion can affect the position of the salient regions. To solve the above problems, this paper proposes a Region-guided Spatial Feature Aggregation Network (RSFAN) for vehicle re-ID, which forces the model to learn the latent information in the minor salient regions. Firstly, a Regional Localization (RL) module is proposed to automatically locate the salient regions without additional auxiliary networks. In addition, to mitigate the misguidance caused by the inaccurate salient regions, a Spatial Feature Aggregation (SFA) module is designed to weaken and enhance the expression of the salient and minor salient regions, respectively. Meanwhile, to enhance the diversity of the minor salient region-related information, a Cross-level Channel Attention (CCA) module is designed to implement cross-level interactions through the channel attention mechanism across different levels. Finally, to constrain the distributional differences between the salient regions and minor salient regions feature, a Distributional Variance (DV) loss is proposed. The extensive experiments show that the RSFAN has a good performance on VeRi-776, VehicleID, VeRi-Wild and Market1501 datasets.