https://github.com/simonwinther/rare-unet
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.
https://github.com/simonwinther/rare-unet
3d-unet adaptive-inference brain-mri consistency-training dynamic-routing hippocampus-segmentation medical-image-segmentation multi-scale rare-unet resolution-aware tumor-segmentation
Last synced: 9 months ago
JSON representation
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.
- Host: GitHub
- URL: https://github.com/simonwinther/rare-unet
- Owner: simonwinther
- License: apache-2.0
- Created: 2025-07-16T09:31:36.000Z (12 months ago)
- Default Branch: master
- Last Pushed: 2025-07-29T12:03:36.000Z (11 months ago)
- Last Synced: 2025-08-20T09:49:25.442Z (10 months ago)
- Topics: 3d-unet, adaptive-inference, brain-mri, consistency-training, dynamic-routing, hippocampus-segmentation, medical-image-segmentation, multi-scale, rare-unet, resolution-aware, tumor-segmentation
- Language: Python
- Homepage:
- Size: 1.38 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0