VisualBackProp: visualizing CNNs for autonomous driving.

Bernhard Firner
Bernhard Firner
Larry D. Jackel
Larry D. Jackel
Karol Zieba
Karol Zieba

arXiv: Computer Vision and Pattern Recognition, (2016)

Cited by: 45|Views59
EI

Abstract:

This paper proposes a new method, that we call VisualBackProp, for visualizing which sets of pixels of the input image contribute most to the predictions made by the convolutional neural network (CNN). The method heavily hinges on exploring the intuition that the feature maps contain less and less irrelevant information to the prediction ...More

Code:

Data:

ZH
Get fulltext within 24h
Bibtex
Your rating :
0

 

Tags
Comments