Journal article icon

Journal article

Understanding Image Representations by Measuring Their Equivariance and Equivalence

Abstract:

Despite the importance of image representations such as histograms of oriented gradients and deep Convolutional Neural Networks (CNN), our theoretical understanding of them remains limited. Aimed at filling this gap, we investigate two key mathematical properties of representations: equivariance and equivalence. Equivariance studies how transformations of the input image are encoded by the representation, invariance being a special case where a transformation has no effect. Equivalence studie...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Publisher's version

Actions


Access Document


Files:
Publisher copy:
10.1007/s11263-018-1098-y

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Oxford college:
New College
More from this funder
Grant:
677195-IDIU Oxford Engineering Science DTA
Publisher:
Springer Publisher's website
Journal:
International Journal of Computer Vision Journal website
Publication date:
2018-05-18
Acceptance date:
2018-04-26
DOI:
EISSN:
1573-1405
ISSN:
0920-5691
Pubs id:
pubs:856183
URN:
uri:2dada857-6f6b-43a2-a2bb-551174a4e9f4
UUID:
uuid:2dada857-6f6b-43a2-a2bb-551174a4e9f4
Local pid:
pubs:856183

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