用于无训练测试时医学图像分割的内存支持协同适应
Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentation
浏览论文内容
中文总结 AI 辅助
研究针对医学图像分割中测试时适应的挑战，提出内存支持协同适应（MSSA）框架，不更新模型参数，通过构建在线内存、文本引导语义先验及跨图像结构对齐实现稳健适应，实验证明其优于现有方法。
中文摘要 AI 辅助
测试时适应（TTA）旨在通过在推理时用未标记的目标数据调整模型来减轻分布偏移。虽然基于视觉语言模型（VLM）的TTA在分类中显示出有前景的结果，但将其扩展到医学图像分割仍具有挑战性。在这种情况下，因噪声、更新驱动学习导致VLM强大的预训练特征退化，使得从优化VLM生成的预测中获得的适应收益往往被抵消，改进有限且不稳定。因此提出内存支持协同适应（MSSA），一种用于医学图像分割的无训练TTA框架。MSSA在不更新模型参数的情况下，动态选择可靠的图像-文本预测来构建在线内存，将其用作文本引导的语义先验，并与跨图像结构对齐相结合以实现稳健适应。具体包括噪声感知内存构建模块和相关性驱动原型对齐模块。在多个医学分割基准上的大量实验表明，MSSA持续改进基于VLM的分割模型，明显优于现有的基于微调的TTA方法，DSC增益高达12.2%，mIoU增益高达11.7%。
英文摘要
Test-time adaptation (TTA) aims to mitigate distribution shifts by adapting models with unlabeled target data at inference time. While TTA with vision-language models (VLMs) has shown promising results in classification, extending it to medical image segmentation remains challenging. In this setting, the adaptation gains from optimizing on VLM-generated predictions are often outweighed by the degradation to the VLM's strong pretrained features caused by noisy, update-driven learning, resulting in limited and unstable improvements. We therefore propose Memory-Supported Synergistic Adaptation (MSSA), a novel training-free TTA framework for medical image segmentation. Without updating model parameters, MSSA dynamically selects reliable image-text predictions to construct an online memory, uses them as text-guided semantic priors, and couples them with cross-image structural alignment for robust adaptation. Specifically, MSSA consists of (i) a noise-aware memory construction module that filters and stabilizes cross-modal predictions, and (ii) a relevance-driven prototype alignment module that aligns the target sample with structurally consistent memory samples and their reliable predictions to improve adaptation. Extensive experiments on multiple medical segmentation benchmarks demonstrate that MSSA consistently improves VLM-based segmentation models and outperforms existing fine-tuning-based TTA methods by a clear margin, with gains of up to 12.2% DSC and 11.7% mIoU. Project page: https://lingrayy.github.io/MSSA/ .
发表机构
- School of Computer Science, University of Nottingham（诺丁汉大学计算机科学学院）
- School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机科学与信息工程学院）
- Information Systems Technology and Design Pillar, Singapore University of Technology and Design（新加坡科技设计大学信息系统技术与设计支柱）
机构由 AI 辅助整理，请以论文原文为准。
