In this work we develop a fast saliency detection method that can be applied to any differentiable image classifier. We train a masking model to manipulate the scores of the classifier by masking salient parts of the input image. Our model generalises well to unseen images and requires a single forward pass to perform saliency detection, therefore suitable for use in real-time systems. We test our approach on CIFAR-10 and ImageNet datasets and show that the produced saliency maps are easily interpretable, sharp, and free of artifacts. We suggest a new metric for saliency and test our method on the ImageNet object localisation task. We achieve results outperforming other weakly supervised methods.
Cite
@article{arxiv.1705.07857,
title = {Real Time Image Saliency for Black Box Classifiers},
author = {Piotr Dabkowski and Yarin Gal},
journal= {arXiv preprint arXiv:1705.07857},
year = {2017}
}