Timezone: »

 
Poster
Real Time Image Saliency for Black Box Classifiers
Piotr Dabkowski · Yarin Gal

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #117 #None

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.

Author Information

Piotr Dabkowski (Cambridge University)
Yarin Gal (University of Oxford)

More from the Same Authors