Conference item icon

Conference item

Warped convolutions: Efficient invariance to spatial transformations

Abstract:

Convolutional Neural Networks (CNNs) are extremely efficient, since they exploit the inherent translation-invariance of natural images. However, translation is just one of a myriad of useful spatial transformations. Can the same efficiency be attained when considering other spatial invariances? Such generalized convolutions have been considered in the past, but at a high computational cost. We present a construction that is simple and exact, yet has the same computational complexity that stan...

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

Actions


Access Document


Files:

Authors


Henriques, JF More by this author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Oxford college:
New College; New College; New College; New College
Publisher:
Proceedings of Machine Learning Research Publisher's website
Publication date:
2017-07-17
Acceptance date:
2017-05-12
Pubs id:
pubs:821529
URN:
uri:7fa292e7-9e11-4df0-be7d-06010f52b900
UUID:
uuid:7fa292e7-9e11-4df0-be7d-06010f52b900
Local pid:
pubs:821529
ISBN:
9781510855144

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