NeurIPS 2017poster809 citations
Real Time Image Saliency for Black Box Classifiers
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.
BibTeX
@inproceedings{NIPS2017_0060ef47,
author = {Dabkowski, Piotr and Gal, Yarin},
booktitle = {Advances in Neural Information Processing Systems},
editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Real Time Image Saliency for Black Box Classifiers},
url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/0060ef47b12160b9198302ebdb144dcf-Paper.pdf},
volume = {30},
year = {2017}
}