Journal article icon

Journal article

Learning deep visual object models from noisy web data: How to make it work

Abstract:

Deep networks thrive when trained on large scale data collections. This has given ImageNet a central role in the development of deep architectures for visual object classification. However, ImageNet was created during a specific period in time, and as such it is prone to aging, as well as dataset bias issues. Moving beyond fixed training datasets will lead to more robust visual systems, especially when deployed on robots in new environments which must train on the objects they encounter there...

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

Actions


Access Document


Files:
Publisher copy:
10.1109/IROS.2017.8206444

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Oxford college:
Pembroke College
Role:
Author
ORCID:
0000-0002-7556-6098
Expand authors...
More from this funder
Grant:
637076 - RoboExNovo (BC, TT)
More from this funder
Grant:
EU FP7 600623 STRANDS (JY, NH) and the CHIST-ERA project ALOOF (BC, NM, JY, NH)
Publisher:
IEEE Publisher's website
Journal:
2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Journal website
Pages:
5564-5571
Publication date:
2017-12-14
Acceptance date:
2017-06-15
DOI:
ISSN:
2153-0866
Pubs id:
pubs:821135
URN:
uri:03b960ec-4922-4d2e-8ea4-4705a572f2c8
UUID:
uuid:03b960ec-4922-4d2e-8ea4-4705a572f2c8
Local pid:
pubs:821135
ISBN:
978-1-5386-2682-5

Terms of use


Metrics


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