Top-down Neural Attention by Excitation Backprop

International Journal of Computer Vision, Volume 126, Issue 10, 2017, Pages 1084-1102.

Cited by: 329|Bibtex|Views100|DOI:https://doi.org/10.1007/s11263-017-1059-x
EI
Other Links: dblp.uni-trier.de|link.springer.com|academic.microsoft.com|arxiv.org

Abstract:

We aim to model the top-down attention of a convolutional neural network (CNN) classifier for generating task-specific attention maps. Inspired by a top-down human visual attention model, we propose a new backpropagation scheme, called Excitation Backprop, to pass along top-down signals downwards in the network hierarchy via a probabilist...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments