Transformer-Based Attention Network for Vehicle Re-Identification

Abstract

Vehicle re-identification (ReID) focuses on searching for images of the same vehicle across different cameras and can be considered as the most fine-grained ID-level classification task. It is fundamentally challenging due to the significant differences in appearance presented by a vehicle with the same ID (especially from different viewpoints) coupled with the subtle differences between vehicles with different IDs. Spatial attention mechanisms that have been proven to be effective in computer vision tasks also play an important role in vehicle ReID. However, they often require expensive key-point labels or suffer from noisy attention masks when trained without key-point labels. In this work, we propose a transformer-based attention network (TAN) for learning spatial attention information and hence for facilitating learning of discriminative features for vehicle ReID. Specifically, in contrast to previous studies that adopted a transformer network, we designed the attention network as an independent branch that can be flexibly utilized in various tasks. Moreover, we combined the TAN with two other branches: one to extract global features that define the image-level structures, and the other to extract the auxiliary side-attribute features that are invariant to viewpoint, such as color, car type, etc. To validate the proposed approach, experiments were conducted on two vehicle datasets (the VeRi-776 and VehicleID datasets) and a person dataset (Market-1501). The experimental results demonstrated that the proposed TAN is effective in improving the performance of both the vehicle and person ReID tasks, and the proposed method achieves state-of-the-art (SOTA) perfomance.

Multi-Adjacent Camera-Based Dangerous Driving Trajectory Recognition for Ultra-Long Highways

“…It can be mainly divided into supervised, metric and unsupervised learning methods. Methods based on supervised learning are further divided into methods based on global features [18,19], local features [20,21] and attention mechanism [22]. The goal of metric learning is to learn a mapping from the original features to the embedding space, such that the objects of the same category are close in the embedding space, and the distance between different categories is far away.…”

Multi-Object Multi-Camera Tracking Based on Deep Learning for Intelligent Transportation: A Review

“…For example, Zhu et al [113] added self-attentive models to each branch of the CNN network for fine-grained recognition of vehicles. To reduce the influence of noise in the image, Lian et al [114] used the attention network based on transformer to extract the global features of vehicle re-ID. Jiang et al [115] studied a global reference attention network.…”

V2ReID: Vision-Outlooker-Based Vehicle Re-Identification

“…Other works enhanced CNNs using Transformers. TANet [80] proposes an attentionbased CNN to explore long-range dependencies. The method is composed of three branches:…”

“…Given the base learning rate (LR base ), we spent 10 epochs linearly increasing LR × 10 −1 → LR. Unless mentioned otherwise, cosine annealing was used as the learning rate scheduler [47,80,96]. Table 6.…”