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:
-
-
(Accepted manuscript, 9.1MB)
-
- Publisher copy:
- 10.1109/ICCV.2019.00304
Why is the content I wish to access not available via ORA?
Bibliographic data (the information relating to research outputs) and full-text items (e.g. articles, theses, reports, etc.) arrive in ORA from several different sources. Unfortunately we are not able to make available the full-text for every research output.
Please contact the ORA team (
) if you have queries regarding unavailable content OR if you are aware of a full-text copy we can make available.
) if you have queries regarding unavailable content OR if you are aware of a full-text copy we can make available.
Content may be unavailable for the following four reasons
-
Version unsuitable
-
We have not obtained a suitable full-text for a given research output. See this page for more information.
-
Recently completed
-
Sometimes content is held in ORA but is unavailable for a fixed period of time to comply with the policies and wishes of rights holders.
-
Permissions
-
All content made available in ORA should comply with relevant rights, such as copyright. See this page for more information.
-
Clearance
-
Some thesis volumes scanned as part of the digitisation scheme funded by Dr Leonard Polonsky are currently unavailable due to sensitive material or uncleared third-party copyright content. We are attempting to contact authors whose theses are affected.
Alternative access to the full-text
You may be able to access the full-text directly from the publisher's website using the 'Publisher Copy' link in the 'Links & Downloads' box from a research output's ORA record page. This method may require an institutional or individual subscription to the journal/resource.
Authors
Bibliographic Details
- 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
Item Description
- Language:
- English
- Keywords:
- Pubs id:
-
1097430
- Local pid:
- pubs:1097430
- Deposit date:
- 2020-05-18
Terms of use
- Copyright holder:
- IEEE
- Copyright date:
- 2019
- Rights statement:
- © 2019 IEEE.
- Notes:
- This paper was presented at the IEEE International Conference on Computer Vision 2019 (ICCV 2019), Seoul, South Korea, October-November 2019. This is the accepted manuscript version of the paper. The final version is available online from IEEE at: https://doi.org/10.1109/ICCV.2019.00304
If you are the owner of this record, you can report an update to it here: Report update to this record