Camera-Aware Differentiated Clustering With Focal Contrastive Learning for Unsupervised Vehicle Re-Identification

Most existing research on vehicle re-identification (Re-ID) focuses on supervised methods, while unsupervised methods that can take advantage of massive unlabeled data are underexplored. Due to the similarity of tasks, unsupervised person Re-ID methods that employ clustering to generate pseudo labels for model training can achieve good performance on unsupervised vehicle Re-ID task. However, vehicle exhibit higher intra-ID compactness and inter-ID separability within camera than person, which has not been exploited to reduce pseudo label noise for unsupervised vehicle Re-ID. To address this issue, we propose a camera-aware differentiated clustering with focal contrastive learning (CDF) method for unsupervised vehicle Re-ID task. Unlike the conventional global clustering approach that adopts a uniform processing strategy for pseudo-label generation, a camera-aware differentiated clustering (CDC) approach is designed to reduce label noise. In CDC, the entire clustering process is divided into two stages: inter-camera and intra-camera clustering, and each stage adopts different clustering strategies that are carefully designed according to the differences in feature distribution within and across cameras. By considering the distribution of pseudo labels generated by CDC, a measure for calculating the reliability of inter-camera and intra-camera pseudo labels is further designed, and a focal contrastive learning loss is proposed to improve the model's ID discrimination ability within and across cameras. Extensive experiments on VeRi-776 and VERI-Wild demonstrate the effectiveness of each designed component and the superiority of the CDF.