Real Time Image Saliency for Black Box Classifiers

Code

• github.com/PiotrDabkowski/pytorch-saliency
  pytorch★ 126
• github.com/zib-iol/merlin-arthur-classifiers
  pytorch★ 1
• github.com/davidGCR/saliencyMapper
  pytorch★ 0
• github.com/karanchahal/SaliencyMapper
  pytorch★ 0

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.

Tasks

Reproductions