Adversarial Continual Learning for Multi-Domain Hippocampal Segmentation
-
Updated
Jul 20, 2021 - Python
Adversarial Continual Learning for Multi-Domain Hippocampal Segmentation
This repository features RARE-UNet a resolution-aware 3D U-Net for adaptive medical segmentation. It uses multi-scale entry blocks and resolution-based routing to dynamically adjust the inference path to input resolution. Combined with consistency-based training, RARE-UNet delivers accurate, efficient segmentation across resolutions.
Official PyTorch code base for our WACV 2025 published paper NCAadapt: Dynamic adaptation with domain-specific Neural Cellular Automata for continual hippocampus segmentation.
Add a description, image, and links to the hippocampus-segmentation topic page so that developers can more easily learn about it.
To associate your repository with the hippocampus-segmentation topic, visit your repo's landing page and select "manage topics."