Boosting Deep Unsupervised Edge Detection via Segment Anything Model

1）使用Adapter对SAM的image encoder进行微调，如下图所示
2）使用Adaptive Progressive Learning优化损失函数，使其可以更好的学习hard sample
3）使用Gradient-guided Pseudo-label Updating来更新pseudo-label

Prompting Segment Anything Model with Domain-Adaptive Prototype for Generalizable Medical Image Segmentation

1）同样使用Adapter进行微调，但是融入了每一层的中间特征
2）提出channel attention filter
3）使用从source domain images中学习的prototype-based memory bank来作为domain adaptive prompt generator

IPLC: Iterative Pseudo Label Correction Guided by SAM for Source-Free Domain Adaptation in Medical Image Segmentation

1）多次使用SAM-Med2D推理，从而生成合适的伪标签