Conference item icon

Conference item

I have seen enough: Transferring parts across categories

Abstract:

The recent successes of deep learning have been possible due to the availability of increasingly large quantities of annotated data. A natural question, therefore, is whether further progress can be indefinitely sustained by annotating more data, or whether there is a saturation point beyond which a problem is essentially solved, or the capacity of a model is saturated. In this paper we examine this question from the viewpoint of learning shareable semantic parts, a fundamental building block...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Publisher's version

Actions


Access Document


Files:

Authors


More by this author
Department:
Oxford, MPLS, Engineering Science
More by this author
Department:
Oxford, MPLS, Engineering Science
Xerox Research Center Europe More from this funder
Publisher:
British Machine Vision Association and Society for Pattern Recognition Publisher's website
Publication date:
2016-09-05
Acceptance date:
2016-05-13
Pubs id:
pubs:656432
URN:
uri:4dc4b9dd-2fc4-4eb6-bfd3-e8d230bf75b9
UUID:
uuid:4dc4b9dd-2fc4-4eb6-bfd3-e8d230bf75b9
Local pid:
pubs:656432

Terms of use


Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP