SAM-GT: SAM as a General Teacher Enhances Medical Image Segmentation by Distilling Only What Matters
Abstract: The Segment Anything Model (SAM) exhibits strong segmentation and generalization capabilities, attracting significant attention in medical image segmentation. Existing research primarily ...
Abstract: Deep convolutional neural networks can extract more accurate structural information via deep architectures to obtain good performance in image super-resolution. However, it is not easy to ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results