Combating the Negative Optimization in Source-Free Domain Adaptive Medical Image Segmentation via Selective Online Self-Training

Wenjuan Zhou, Wei Chen, Yulin He, Chen Li

Abstract: Self-Training has proven to be a simple yet effective framework in source-free domain adaptation (SFDA) for medical image segmentation. However, prevalent domain discrepancies and privacy restrictions on source domain data can lead to the negative optimization problem. Current methods predominantly focus on rigorous pseudo-label quality assessment, yet they often overlook the specific prior knowledge inherent to medical images and the potential of online self-training to combat negative optimization. To address these gaps, this paper introduces a selective online self-training method, tackling the issue from both the pseudo-label selection and learning stages. In the selection stage, we identify a domain-invariant prior related to organ shape, and propose a class-prior guided selection mechanism to mitigate class imbalance in pseudo-labels. In the learning stage, we introduce a strategy to selectively update the teacher model based on evolutionary state feedback generated by the student model. Extensive experiments conducted on two widely used benchmarks show the effectiveness of our method, which achieves notable 2.0% and 4.1% Dice improvements.

External IDs:dblp:conf/icmcs/ZhouCHL25