VisualBackProp: visualizing CNNs for autonomous driving.
arXiv: Computer Vision and Pattern Recognition, (2016)
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
Full Text (Upload PDF)
PPT (Upload PPT)