Improved Mutual Mean-Teaching
for Unsupervised Domain Adaptive Re-ID
Abstract
In this technical report, we present our submission to the VisDA Challenge in ECCV 2020 and we achieved one of the top-performing results on the leaderboard. Our solution is based on Structured Domain Adaptation (SDA) and Mutual Mean-Teaching (MMT) frameworks. SDA, a domain-translation-based framework, focuses on carefully translating the source-domain images to the target domain. MMT, a pseudo-label-based framework, focuses on conducting pseudo label refinery with robust soft labels. Specifically, there are three main steps in our training pipeline. (i) We adopt SDA to generate source-to-target translated images, and (ii) such images serve as informative training samples to pre-train the network. (iii) The pre-trained network is further fine-tuned by MMT on the target domain. Note that we design an improved MMT (dubbed MMT+) to further mitigate the label noise by modeling inter-sample relations across two domains and maintaining the instance discrimination. Our proposed method achieved 74.78% accuracies in terms of mAP, ranked the 2nd place out of 153 teams.
Materials
Citation
@misc{ge2020improved,
title={Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID},
author={Yixiao Ge and Shijie Yu and Dapeng Chen},
year={2020},
eprint={2008.10313},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
@inproceedings{ge2020mutual,
title={Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification},
author={Yixiao Ge and Dapeng Chen and Hongsheng Li},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://openreview.net/forum?id=rJlnOhVYPS}
}
@misc{ge2020structured,
title={Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID},
author={Yixiao Ge and Feng Zhu and Rui Zhao and Hongsheng Li},
year={2020},
eprint={2003.06650},
archivePrefix={arXiv},
primaryClass={cs.CV}
}