Semi-supervised domain adaptation is a technique to build a classifier for a target domain by modifying a classifier in another (source) domain using many unlabeled samples and a small number of labeled samples from the target domain. In this paper, we develop a semi-supervised domain adaptation method, which has robustness to class-imbalanced situations, which are common in medical image classification tasks. For robustness, we propose a weakly-supervised clustering pipeline to obtain high-purity clusters and utilize the clusters in representation learning for domain adaptation. The proposed method showed state-of-the-art performance in the experiment using severely class-imbalanced pathological image patches.
@article{arxiv.2303.01283,
title = {Cluster-Guided Semi-Supervised Domain Adaptation for Imbalanced Medical Image Classification},
author = {Shota Harada and Ryoma Bise and Kengo Araki and Akihiko Yoshizawa and Kazuhiro Terada and Mariyo Kurata and Naoki Nakajima and Hiroyuki Abe and Tetsuo Ushiku and Seiichi Uchida},
journal= {arXiv preprint arXiv:2303.01283},
year = {2023}
}