Conference item icon

Conference item

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 i...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted manuscript

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Computer Science
Role:
Author
Publisher:
NIPS Foundation Publisher's website
Publication date:
2018-07-01
Acceptance date:
2017-09-04
Pubs id:
pubs:746865
URN:
uri:28800c28-44b0-42e5-b32c-8c66a83bc389
UUID:
uuid:28800c28-44b0-42e5-b32c-8c66a83bc389
Local pid:
pubs:746865

Terms of use


Metrics


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP