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.

The paper proposes an approach to learn saliency masks. The proposed approach is based on a neural network and can process multiple images per second (i.e. it is fast). To me the paper is borderline, I would not object rejection or acceptance. I really believe in the concept of learning to explain a model and I think the paper has some good ideas. There are no obvious mistakes but there are clear limitations.