Improving Deep Learning Interpretability by Saliency Guided Training.

Aya Abdelsalam Ismail Héctor Corrada Bravo Soheil Feizi

Published in: CoRR (2021)

Keyphrases

deep learning
deep architectures
restricted boltzmann machine
unsupervised learning
unsupervised feature learning
machine learning
deep belief networks
supervised learning
weakly supervised
training samples
mental models
appearance model
long range
graph cuts
viewpoint
pattern recognition
computer vision