Multi-level mutual supervision for cross-domain Person Re-identification

The challenges of cross-domain person re-identification mainly derive from two aspects: (1) The missing of target data labels. (2) The bias between source domain and target domain. Most of existing works focus on only one problem in the above two or deal with them separately. In this paper, we propose a new approach referred as to multi-level mutual supervision to achieve full utilization of labeled source data and unlabeled target data. Along this approach, we construct a dual-branch framework of which the upper branch is trained with original source data and target data while the lower branch is trained with augmented source data and target data. By applying common-pseudo-label and Maximum Mean Discrepancy (MMD) loss in our framework, the mutual supervision in multi levels is achieved. The results show that our model achieves SOTA performance on multiple popular benchmark datasets. •Dual-branch structure generates features with stronger representation ability.•Different training streams produce diverse features.•Supervision is realized in feature level, dataset level and domain level.•Finding the optimal calculation strategy of MMD to reduce the gap between domains.