持续对齐用于SAM：重新思考面向持续学习的医学图像分割的基础模型
Continual Alignment for SAM: Rethinking Foundation Models for Medical Image Segmentation in Continual Learning
AI总结：
CA-SAM通过引入对齐层，实现了在持续学习中高效适应医学图像分割，提升性能并减少计算开销。
摘要：
在医学图像分割中，不同机构之间的隐私政策差异往往使得在汇总数据集上联合训练不可行，这促使了在数据流中进行持续图像分割学习，以避免灾难性遗忘。虽然Segment Anything Model（SAM）提供了强大的零样本先验，并已被广泛微调到下游任务中，但其较大的参数数量和计算开销对实际部署构成了挑战。本文证明，一旦SAM范式在计算效率和性能之间达到平衡，其具有极大的潜力。为此，我们引入了对齐层，这是一个轻量级、即插即用的模块，用于对编码器-解码器特征分布进行对齐，以高效地将SAM适应到特定的医学图像中，提高准确性的同时减少计算量。基于SAM和对齐层，我们随后提出了持续对齐用于SAM（CA-SAM），一种持续学习策略，能够自动适应合适的对齐层以缓解灾难性遗忘，同时利用SAM的零样本先验来在未见的医学数据集上保持强大的性能。在九个医学分割数据集上进行实验，以持续学习场景为背景，CA-SAM实现了最先进的性能。我们的代码、模型和数据集将在https://github.com/azzzzyo/Continual-Alignment-for-SAM上发布。
英文摘要：
In medical image segmentation, heterogeneous privacy policies across institutions often make joint training on pooled datasets infeasible, motivating continual image segmentation-learning from data streams without catastrophic forgetting. While the Segment Anything Model (SAM) offers strong zero-shot priors and has been widely fine-tuned across downstream tasks, its large parameter count and computational overhead challenge practical deployment. This paper demonstrates that the SAM paradigm is highly promising once its computational efficiency and performance can be balanced. To this end, we introduce the Alignment Layer, a lightweight, plug-and-play module which aligns encoder-decoder feature distributions to efficiently adapt SAM to specific medical images, improving accuracy while reducing computation. Building on SAM and the Alignment Layer, we then propose Continual Alignment for SAM (CA-SAM), a continual learning strategy that automatically adapts the appropriate Alignment Layer to mitigate catastrophic forgetting, while leveraging SAM's zero-shot priors to preserve strong performance on unseen medical datasets. Experimented across nine medical segmentation datasets under continual-learning scenario, CA-SAM achieves state-of-the-art performance. Our code, models and datasets will be released on \mbox{https://github.com/azzzzyo/Continual-Alignment-for-SAM.}
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。
