Conference item icon

Conference item

Understanding deep networks via extremal perturbations and smooth masks

Abstract:

Attribution is the problem of finding which parts of an image are the most responsible for the output of a deep neural network. An important family of attribution methods is based on measuring the effect of perturbations applied to the input image, either via exhaustive search or by finding representative perturbations via optimization. In this paper, we discuss some of the shortcomings of existing approaches to perturbation analysis and address them by introducing the concept of extremal per...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1109/ICCV.2019.00304

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
Publisher:
IEEE Publisher's website
Pages:
2950-2958
Host title:
Proceedings of the IEEE International Conference on Computer Vision
Publication date:
2020-02-27
Acceptance date:
2019-07-22
Event title:
IEEE International Conference on Computer Vision 2019 (ICCV 2019)
Event location:
Seoul, South Korea
Event website:
http://iccv2019.thecvf.com/
Event start date:
2019-10-27T00:00:00Z
Event end date:
2019-11-02T00:00:00Z
DOI:
EISBN:
9781728148038
EISSN:
2380-7504
ISSN:
1550-5499
ISBN:
9781728148045
Language:
English
Keywords:
Pubs id:
1097430
Local pid:
pubs:1097430
Deposit date:
2020-05-18

Terms of use


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