提出双学生切换框架，提升医学图像分割的伪标签质量。
Adaptive Knowledge Transferring with Switching Dual-Student Framework for Semi-Supervised Medical Image Segmentation
- 动态切换可靠学生，避免错误传播
- 使用加权移动平均优化教师更新，提升伪标签精度
- 无需修改模型即可接入，适合医疗影像场景
教师-学生框架在半监督医学图像分割中表现优异，但受限于师生间强相关性及不可靠的知识传递。为此，本文提出一种新型切换双学生架构，在每轮迭代中选择最可靠的学生产生协同，防止错误累积。同时引入基于损失的指数移动平均策略，动态确保教师吸收学生中的有效信息，提升伪标签质量。所提方法为即插即用框架，在3D医学图像分割数据集上显著优于现有先进方法，验证了其在有限标注下的高分割精度能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。