Cross-Resolution Person Re-Identification via Deep Group-Aware Representation Learning
Xiang Ye, Guangwei Gao · 2022 26th International Conference on Pattern Recognition (ICPR) · 2022
Person re-identification (Re-ID) aims to identify the same person from samples taken by different cameras. However, in practical application scenarios, due to the quality of the camera equipment and the distance between the camera and the pedestrian, the captured pedestrian images usually have different resolutions, which will cause the mismatch problem of person Re-ID. To mitigate the resolution discrepancy issue, in this paper, we propose a method called deep group-aware representation learning (DGRL) for effective Re-ID. Firstly, We use the residual Transformer block in the feature extraction stage to thoroughly extract richer local and global information from variable resolution shallow images. Then our proposed multi-layered group-aware representation (MGAR) scheme can generate diverse representations different from the main branch, thereby improving the representation capability of the deeply embedded features. In addition, we calculate the kullback leibler divergence loss (KLDivLoss) values on the probability prediction outputs of any two branches, forcing the entire network to be well optimized. Plenty of evaluations on four benchmark datasets have demonstrated the effectiveness of our method.