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
Actions
Authors
Bibliographic Details
- Publisher:
- NIPS Foundation Publisher's website
- Journal:
- Advances in Neural Information Processing Systems 31 (NIPS 2017) Journal website
- Host title:
- Advances in Neural Information Processing Systems 31 (NIPS 2017)
- Publication date:
- 2018-07-01
- Acceptance date:
- 2017-09-04
- Source identifiers:
-
746865
Item Description
- Pubs id:
-
pubs:746865
- UUID:
-
uuid:28800c28-44b0-42e5-b32c-8c66a83bc389
- Local pid:
- pubs:746865
- Deposit date:
- 2017-11-18
Terms of use
- Copyright holder:
- Neural Information Processing Systems Foundation, Inc
- Copyright date:
- 2018
- Notes:
- © 2018 Neural Information Processing Systems Foundation, Inc. This is the accepted manuscript version of the article. The final version is available online from Neural Information Processing Systems Foundation, Inc. at: https://papers.nips.cc/paper/7272-real-time-image-saliency-for-black-box-classifiers
If you are the owner of this record, you can report an update to it here: Report update to this record