Conference item icon

Conference item

Efficient parametrization of multi-domain deep neural networks

Abstract:

A practical limitation of deep neural networks is their high degree of specialization to a single task and visual domain. Recently, inspired by the successes of transfer learning, several authors have proposed to learn instead universal feature extractors that, used as the first stage of any deep network, work well for several tasks and domains simultaneously. Nevertheless, such universal features are still somewhat inferior to specialized networks.


To overcome this limitation...

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

Actions


Access Document


Files:
Publisher copy:
10.1109/CVPR.2018.00847

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
New College
Role:
Author
More from this funder
Name:
European Research Council
Grant:
638009
More from this funder
Name:
Engineering & Physical Sciences Research Council
Grant:
EP/M013774/1
Publisher:
Institute of Electrical and Electronics Engineers
Host title:
Conference on Computer Vision and Pattern Recognition (CVPR 2018)
Journal:
Conference on Computer Vision and Pattern Recognition (CVPR 2018) More from this journal
Publication date:
2018-12-17
Acceptance date:
2018-02-28
DOI:
Pubs id:
pubs:859554
UUID:
uuid:a8e2ae12-2c29-4620-9127-31dc05323add
Local pid:
pubs:859554
Source identifiers:
859554
Deposit date:
2018-06-27

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