In medical image analysis, semi-supervised learning is an effective method to extract knowledge from a small amount of labeled data and a large amount of unlabeled data. This paper focuses on a popular pipeline known as self learning, and points out a weakness named lazy learning that refers to the difficulty for a model to learn from the pseudo labels generated by itself. To alleviate this issue, we propose ATSO, an asynchronous version of teacher-student optimization. ATSO partitions the unlabeled data into two subsets and alternately uses one subset to fine-tune the model and updates the label on the other subset. We evaluate ATSO on two popular medical image segmentation datasets and show its superior performance in various semi-supervised settings. With slight modification, ATSO transfers well to natural image segmentation for autonomous driving data.
@article{arxiv.2006.13461,
title = {ATSO: Asynchronous Teacher-Student Optimization for Semi-Supervised Medical Image Segmentation},
author = {Xinyue Huo and Lingxi Xie and Jianzhong He and Zijie Yang and Qi Tian},
journal= {arXiv preprint arXiv:2006.13461},
year = {2020}
}