Skip to yearly menu bar Skip to main content


Poster

Real Time Image Saliency for Black Box Classifiers

Piotr Dabkowski · Yarin Gal

Pacific Ballroom #117

Keywords: [ Deep Learning ] [ Computer Vision ] [ Visualization/Expository Techniques for Deep Networks ]


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.

Live content is unavailable. Log in and register to view live content