Conference item icon

Conference item

Multi-task learning using uncertainty to weigh losses for scene geometry and semantics

Abstract:

Numerous deep learning applications benefit from multitask learning with multiple regression and classification objectives. In this paper we make the observation that the performance of such systems is strongly dependent on the relative weighting between each task's loss. Tuning these weights by hand is a difficult and expensive process, making multi-task learning prohibitive in practice. We propose a principled approach to multi-task deep learning which weighs multiple loss functions by cons...

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

Actions


Access Document


Files:
Publisher copy:
10.1109/cvpr.2018.00781

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Oxford college:
Christ Church
Role:
Author
Publisher:
IEEE Publisher's website
Pages:
7482-7491
Host title:
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Publication date:
2018-12-17
Event title:
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018)
Event location:
Salt Lake City, Utah, USA
Event website:
http://cvpr2018.thecvf.com/
Event start date:
2018-06-18T00:00:00Z
Event end date:
2018-06-22T00:00:00Z
DOI:
EISSN:
2575-7075
ISSN:
1063-6919
Language:
English
Keywords:
Pubs id:
1105069
Local pid:
pubs:1105069
Deposit date:
2020-05-15

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