Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
This work addresses interpretability for researchers and practitioners in computer vision, offering incremental improvements by connecting gradient-based methods to deconvolutional networks.
The paper tackles the problem of visualizing image classification models using deep Convolutional Networks by introducing gradient-based techniques to generate class-maximizing images and class-specific saliency maps, and demonstrates their application in weakly supervised object segmentation.
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].