Adaptive Knowledge Transferring with Switching Dual-Student Framework for Semi-Supervised Medical Image Segmentation

TL;DR

This paper proposes a novel switching dual-student framework with loss-aware EMA for semi-supervised medical image segmentation, significantly improving pseudo-label quality and segmentation accuracy over existing methods.

Contribution

Introduces a switching dual-student architecture and loss-aware EMA strategy to enhance knowledge transfer and collaboration in semi-supervised medical image segmentation.

Findings

Outperforms state-of-the-art semi-supervised methods on 3D medical datasets.

Effectively selects the most reliable student to prevent error reinforcement.

Improves segmentation accuracy with limited supervision.

Abstract

Teacher-student frameworks have emerged as a leading approach in semi-supervised medical image segmentation, demonstrating strong performance across various tasks. However, the learning effects are still limited by the strong correlation and unreliable knowledge transfer process between teacher and student networks. To overcome this limitation, we introduce a novel switching Dual-Student architecture that strategically selects the most reliable student at each iteration to enhance dual-student collaboration and prevent error reinforcement. We also introduce a strategy of Loss-Aware Exponential Moving Average to dynamically ensure that the teacher absorbs meaningful information from students, improving the quality of pseudo-labels. Our plug-and-play framework is extensively evaluated on 3D medical image segmentation datasets, where it outperforms state-of-the-art semi-supervised methods, demonstrating its effectiveness in improving segmentation accuracy under limited supervision.