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 same photograph, since faces from the same photograph are more likely to be from the same family. In this paper we investigate the influence of this artefactual data inference in publis...

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

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:
MSD
Department:
Physiology Anatomy & Genetics
Role:
Author
ORCID:
0000-0002-2887-2068
Publisher:
Springer Publisher's website
Journal:
Lecture Notes in Computer Science Journal website
Volume:
11363
Pages:
654-668
Series:
Lecture Notes in Computer Science
Host title:
Computer Vision – ACCV 2018
Publication date:
2019-05-29
Acceptance date:
2018-09-21
DOI:
Source identifiers:
938383
ISBN:
9783030208936
Keywords:
Pubs id:
pubs:938383
UUID:
uuid:63942c59-387f-4f94-9b19-bf15df8d3609
Local pid:
pubs:938383
Deposit date:
2018-11-06

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