Multi-attribute adaptive aggregation transformer for vehicle re-identification

• A vehicle attribute transformer for vehicle re-identification is proposed, which can aggregate the attributes of vehicle model, color and viewpoint adaptively. • A multi-sample dispersion triplet loss is designed to optimize the proposed transformer network, which can consider richer positive and negative sample information. • Extensive experiments on popular vehicle re-identification datasets verify that the proposed method can achieve state-of-the-art performance. With the continuous development of intelligent transportation systems, vehicle-related fields have emerged a research boom in detection, tracking, and retrieval. Vehicle re-identification aims to judge whether a specific vehicle appears in a video stream, which is a popular research direction. Previous researches have proven that the transformer is an efficient method in computer vision, which treats a visual image as a series of patch sequences. However, an efficient vehicle re-identification should consider the image feature and the attribute feature simultaneously. In this work, we propose a vehicle attribute transformer (VAT) for vehicle re-identification. First, we consider color and model as the most intuitive attributes of the vehicle, the vehicle color and model are relatively stable and easy to distinguish. Therefore, the color feature and the model feature are embedded in a transformer. Second, we consider that the shooting angle of each image may be different, so we encode the viewpoint of the vehicle image as another additional attribute. Besides, different attributes are supposed to have different importance. Based on this, we design a multi-attribute adaptive aggregation network, which can compare different attributes and assign different weights to the corresponding features. Finally, to optimize the proposed transformer network, we design a multi-sample dispersion triplet (MDT) loss. Not only the hardest samples based on hard mining strategy, but also some extra positive samples and negative samples are considered in this loss. The dispersion of multi-sample is utilized to dynamically adjust the loss, which can guide the network to learn more optimized division for feature space. Extensive experiments on popular vehicle re-identification datasets verify that the proposed method can achieve state-of-the-art performance.