Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Computer Vision and Pattern Recognition
2014-04-22 v2
Abstract
This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets). We consider two visualisation techniques, based on computing the gradient of the class score with respect to the input image. The first one generates an image, which maximises the class score [Erhan et al., 2009], thus visualising the notion of the class, captured by a ConvNet. The second technique computes a class saliency map, specific to a given image and class. We show that such maps can be employed for weakly supervised object segmentation using classification ConvNets. Finally, we establish the connection between the gradient-based ConvNet visualisation methods and deconvolutional networks [Zeiler et al., 2013].
Cite
@article{arxiv.1312.6034,
title = {Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps},
author = {Karen Simonyan and Andrea Vedaldi and Andrew Zisserman},
journal= {arXiv preprint arXiv:1312.6034},
year = {2014}
}