Conference item icon

Conference item

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. Aiming at filling this gap, we investigate three key mathematical properties of representations: equivariance, invariance, 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. Eq...

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

Actions


Access Document


Publisher copy:
10.1109/CVPR.2015.7298701

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Department of Engineering Science
Oxford college:
St Anne's College
Role:
Author
ORCID:
0000-0001-6119-0045
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
New College
Role:
Author
Publisher:
IEEE
Host title:
2015 IEEE Conference on computer vision and pattern recognition
Journal:
2015 IEEE Conference on computer vision and pattern recognition More from this journal
Pages:
991-999
Publication date:
2015-10-15
DOI:
ISSN:
1063-6919
ISBN:
9781467369640
Keywords:
Pubs id:
pubs:581640
UUID:
uuid:ce52d423-ada8-4a57-8526-21ba12d2c3b9
Local pid:
pubs:581640
Source identifiers:
581640
Deposit date:
2018-11-22

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