C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation
CVPR, pp. 4125-4134, 2019.
We propose coarse-to-fine neural architecture search to automatically search a 3D segmentation network from scratch without inconsistency on network size or input size
3D convolution neural networks (CNN) have been proved very successful in parsing organs or tumours in 3D medical images, but it remains sophisticated and time-consuming to choose or design proper 3D networks given different task contexts. Recently, Neural Architecture Search (NAS) is proposed to solve this problem by searching for the b...More
PPT (Upload PPT)