Conference item icon

Conference item

From same photo: Cheating on visual kinship challenges

Abstract:

With the propensity for deep learning models to learn unintended signals from data sets there is always the possibility that the network can “cheat” in order to solve a task. In the instance of data sets for visual kinship verification, one such unintended signal could be that the faces are cropped from the...

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

Actions


Access Document


Files:
Publisher copy:
10.1007/978-3-030-20893-6_41

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Department of Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Department of Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
Medical Sciences Division
Department:
Women's and Reproductive Health
Role:
Author
ORCID:
0000-0002-2887-2068
More from this funder
Grant:
Seebibyte EP/M013774/1
Systems Biology DTC EP/G03706X/1
Publisher:
Springer Publisher's website
Volume:
11363
Pages:
654-668
Series:
Lecture Notes in Computer Science
Publication date:
2019-05-29
Acceptance date:
2018-09-21
DOI:
Pubs id:
pubs:938383
URN:
uri:63942c59-387f-4f94-9b19-bf15df8d3609
UUID:
uuid:63942c59-387f-4f94-9b19-bf15df8d3609
Local pid:
pubs:938383
ISBN:
9783030208936

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