arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.24366cs.CV
收藏

具有切换双学生框架的自适应知识转移用于半监督医学图像分割

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

North Carolina A&T State University(北卡罗来纳农工州立大学);Carnegie Mellon University(卡内基梅隆大学);Ho Chi Minh University of Technology(胡志明市理工大学);University of Pittsburgh(匹兹堡大学);University of Alabama at Birmingham(阿拉巴马大学伯明翰分校)

Hoang-Thien Nguyen, Thanh-Huy Nguyen, Ba-Thinh Lam, Vi Vu, Bach X. Nguyen, Jianhua Xing, Tianyang Wang, Xingjian Li, Min Xu

AI总结:

本文提出了一种切换双学生框架,通过动态选择可靠学生和损失感知移动平均策略,提升半监督医学图像分割的性能。

摘要:

教师-学生框架已成为半监督医学图像分割中的领先方法,在各种任务上表现出强大的性能。然而,学习效果仍然受到教师和学生网络之间强相关性和不可靠的知识转移过程的限制。为了解决这一限制,我们引入了一种新的切换双学生架构,该架构在每次迭代中战略性地选择最可靠的student,以增强双学生协作并防止错误强化。我们还引入了一种损失感知指数移动平均策略,动态确保教师从学生中吸收有意义的信息,从而提高伪标签的质量。我们的即插即用框架在3D医学图像分割数据集上进行了广泛评估,其中它优于最先进的半监督方法,证明了其在有限监督下提高分割准确性方面的有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑