miccaiif / DifABAL

PyTorch implementation of our paper "Rethinking Deep Active Learning for Medical Image Segmentation: A Diffusion and Angle-based Framework"

🍟 DifABAL

This is a PyTorch implementation of our paper "Rethinking Deep Active Learning for Medical Image Segmentation: A Diffusion and Angle-based Framework":

For Diffusion-based Feature Extraction:

• We refer to the Diffae for diffusion-based self-supervised training and feature extraction.

For Angle-based Sampling:

• We release a demo in Jupyter Notebook ABAL Sampler. More comparative sampling methods could be found in Comparative Samplers.

Contact Information

If you have any question, please email to me [e-mail].