Self-Mimic Mutual-Distillation for Cross-Modality Person Re-Identification
Lists
Only you see this
Abstract
Cross-modality person re-identification is a newly rising and challenging problem, as there is a significant gap between the visible and infrared images. Though recent methods rapidly narrow the gap, the intra-modality variance is often ignored before inter-modality alignment. In this paper, we study this problem in the knowledge distillation perspective and design a self-mimic mutual-distillation method to reduce the discrepancy of each person from intra-modality feature alignment to cross-modality feature alignment. For intra-modality feature alignment, the self-mimic mechanism is implemented to simultaneously learn globally viewed, stable, and distinguish prototypes for each ID and minimize the intra-modality discrepancy. For inter-modality feature alignment, the mutual distillation is conducted to minimize the cross-modality distribution discrepancy of each person. Extensive experimental results on SYSU-MM01 and RegDB demonstrate that the proposed method achieves the best performance, outperforming state-of-the-art methods by a large margin without adding extra network parameters to the baseline. Especially, on the SYSU-MM01 dataset, our method achieves 64.8% Rank-1 and 60.2% mAP with significant gains over the latest related method.
BibTeX
@inproceedings{zhang2022self,
author = {Demao Zhang and Ming Hong and Zhou Ye and Zheng Wang and Zhizhong Zhang and Xiaotong Luo and Yuan Xie and Yanyun Qu},
title = {{Self-Mimic Mutual-Distillation for Cross-Modality Person Re-Identification}},
booktitle = {ICME},
year = {2022},
doi = {10.1109/icme52920.2022.9859875},
}Loading related content...