GraphMDN: Leveraging graph structure and deep learning to solve inverse problems.

Tuomas P. Oikarinen Daniel C. Hannah Sohrob Kazerounian

Published in: IJCNN (2021)

Keyphrases

graph structure
deep learning
inverse problems
image reconstruction
unsupervised learning
global optimization
graphical models
machine learning
convex optimization
optimization problems
directed graph
optimization methods
superpixels
evolutionary algorithm
conditional random fields
weakly supervised
early vision