Multiscale methods for neural image processing

Monday, October 22, 2018 - 10:05am - 10:55am
Keller 3-180
Tom Goldstein (University of Maryland)
We present Stacked U-Nets, a neural net architecture that combines the information globalization properties of multigrid solvers with the expressive power of neural nets. Stacked U-Nets achieve state of the art performance on image segmentation using a simple architecture with relatively few parameters.