Deep semi-supervised segmentation with weight-averaged consistency targets

07/12/2018
by   Christian S. Perone, et al.
0

Recently proposed techniques for semi-supervised learning such as Temporal Ensembling and Mean Teacher have achieved state-of-the-art results in many important classification benchmarks. In this work, we expand the Mean Teacher approach to segmentation tasks and show that it can bring important improvements in a realistic small data regime using a publicly available multi-center dataset from the Magnetic Resonance Imaging (MRI) domain. We also devise a method to solve the problems that arise when using traditional data augmentation strategies for segmentation tasks on our new training scheme.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset