- Author
- Year
- 2017
- Title
- Exploiting saliency for object segmentation from image level labels
- Event
- 2017 IEEE Conference on Computer Vision and Pattern Recognition
- Book/source title
- 30th IEEE Conference on Computer Vision and Pattern Recognition
- Book/source subtitle
- CVPR 2017 : 21-26 July 2016, Honolulu, Hawaii : proceedings
- Pages (from-to)
- 5038-5047
- Publisher
- Piscataway, NJ: IEEE
- ISBN
- 9781538604588
- ISBN (electronic)
- 9781538604571
- Document type
- Conference contribution
- Faculty
- Faculty of Science (FNWI)
- Institute
- Informatics Institute (IVI)
- Abstract
-
There have been remarkable improvements in the semantic labelling task in the recent years. However, the state of the art methods rely on large-scale pixel-level annotations. This paper studies the problem of training a pixel-wise semantic labeller network from image-level annotations of the present object classes. Recently, it has been shown that high quality seeds indicating discriminative object regions can be obtained from image-level labels. Without additional information, obtaining the full extent of the object is an inherently ill-posed problem due to co-occurrences. We propose using a saliency model as additional information and hereby exploit prior knowledge on the object extent and image statistics. We show how to combine both information sources in order to recover 80% of the fully supervised performance - which is the new state of the art in weakly supervised training for pixel-wise semantic labelling.
- URL
- go to publisher's site
- Link
- Accepted author manuscript
- Language
- English
- Persistent Identifier
- https://hdl.handle.net/11245.1/04c78344-1b12-4c21-a098-4a8fa796dc10
- Downloads
-
1701.08261(Accepted author manuscript)
Disclaimer/Complaints regulations
If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library, or send a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible.