Conference item icon

Conference item

Multi-task self-supervised visual learning

Abstract:

We investigate methods for combining multiple self-supervised tasks-i.e., supervised tasks where data can be collected without manual labeling-in order to train a single visual representation. First, we provide an apples-to-apples comparison of four different self-supervised tasks using the very deep ResNet-101 architecture. We then combine tasks to jointly train a network. We also explore lasso regularization to encourage the network to factorize the information in its representation, and me...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted Manuscript

Actions


Access Document


Files:
Publisher copy:
10.1109/iccv.2017.226

Authors


Doersch, C More by this author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Oxford college:
Brasenose College
ORCID:
0000-0002-8945-8573
Publisher:
IEEE Explore Publisher's website
Publication date:
2017-12-25
Acceptance date:
2017-07-17
DOI:
ISSN:
1550-5499
Pubs id:
pubs:829573
URN:
uri:f7dca138-b143-4c6a-a96a-c79faba3388c
UUID:
uuid:f7dca138-b143-4c6a-a96a-c79faba3388c
Local pid:
pubs:829573

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