In the field of intelligent transportation, vehicle re-identification (Re-ID) aims to accurately search for target vehicles from a large-scale vehicle gallery. Vehicle images tend to have more similar appearance and smaller differences among them. To address the challenges of vehicle re-recognition, we propose a differential attention based dual-branch vehicle re-identification network. Specifically, to suppress the environmental noise interference, we propose a spatial and channel attention mechanism of differential attention. Differential attention consists of difference spatial attention (DSA) and difference channel attention (DCA). We use the difference between a pair of feature maps obtained by double branching as a noise suppression factor. The experimental results show that the mAP and rank-k indicators of the model on VeRi-776 and the VehicleID are better than the results of the existing vehicle re-identification algorithms, which verifies the algorithm’s effectiveness.