English

Real Time Image Saliency for Black Box Classifiers

Machine Learning 2017-05-23 v1

Abstract

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}
}
R2 v1 2026-06-22T19:55:07.293Z