Efficient Bayesian Uncertainty Estimation for nnU-Net

no code implementations • 12 Dec 2022 • Yidong Zhao, Changchun Yang, Artur Schweidtmann, Qian Tao

Different from previous baseline methods such as Monte Carlo Dropout and mean-field Bayesian Neural Networks, our proposed method does not require a variational architecture and keeps the original nnU-Net architecture intact, thereby preserving its excellent performance and ease of use.

Image Segmentation Medical Image Segmentation +2