Unsupervised Domain Adaptive Person Re-Identification via Human Learning Imitation
This addresses domain adaptation for person re-identification, an incremental improvement over existing teacher-student methods.
The paper tackles unsupervised domain adaptive person re-identification by proposing a Human Learning Imitation framework that adaptively updates learning materials, selectively imitates teacher behaviors, and analyzes structures, achieving efficacy on three benchmark datasets.
Unsupervised domain adaptive person re-identification has received significant attention due to its high practical value. In past years, by following the clustering and finetuning paradigm, researchers propose to utilize the teacher-student framework in their methods to decrease the domain gap between different person re-identification datasets. Inspired by recent teacher-student framework based methods, which try to mimic the human learning process either by making the student directly copy behavior from the teacher or selecting reliable learning materials, we propose to conduct further exploration to imitate the human learning process from different aspects, \textit{i.e.}, adaptively updating learning materials, selectively imitating teacher behaviors, and analyzing learning materials structures. The explored three components, collaborate together to constitute a new method for unsupervised domain adaptive person re-identification, which is called Human Learning Imitation framework. The experimental results on three benchmark datasets demonstrate the efficacy of our proposed method.