VisualBackProp: efficient visualization of CNNs

Bernhard Firner
Bernhard Firner
Larry Jackel
Larry Jackel
Karol Zieba
Karol Zieba

arXiv: Computer Vision and Pattern Recognition, 2018.

被引用26|浏览54

摘要

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 ...更多

代码

数据

ZH
24小时获取PDF
引用
您的评分 :
0

 

标签
评论