Weakly-Supervised Domain Adaptation with Proportion-Constrained Pseudo-Labeling

TL;DR

This paper introduces a weakly-supervised domain adaptation technique that uses class proportion information to improve model performance across different medical datasets, especially when class distributions vary.

Contribution

It proposes a novel proportion-constrained pseudo-labeling approach that leverages target domain class proportions, enhancing adaptation without extra annotations.

Findings

Outperforms semi-supervised methods on endoscopic datasets

Effective even with 5% labeled target data

Robust to noisy class proportion labels

Abstract

Domain shift is a significant challenge in machine learning, particularly in medical applications where data distributions differ across institutions due to variations in data collection practices, equipment, and procedures. This can degrade performance when models trained on source domain data are applied to the target domain. Domain adaptation methods have been widely studied to address this issue, but most struggle when class proportions between the source and target domains differ. In this paper, we propose a weakly-supervised domain adaptation method that leverages class proportion information from the target domain, which is often accessible in medical datasets through prior knowledge or statistical reports. Our method assigns pseudo-labels to the unlabeled target data based on class proportion (called proportion-constrained pseudo-labeling), improving performance without the need for additional annotations. Experiments on two endoscopic datasets demonstrate that our method outperforms semi-supervised domain adaptation techniques, even when 5% of the target domain is labeled. Additionally, the experimental results with noisy proportion labels highlight the robustness of our method, further demonstrating its effectiveness in real-world application scenarios.