Conference item icon

Conference item

Learning covariant feature detectors

Abstract:

Local covariant feature detection, namely the problem of extracting viewpoint invariant features from images, has so far largely resisted the application of machine learning techniques. In this paper, we propose the first fully general formulation for learning local covariant feature detectors. We propose to cast detection as a regression problem, enabling the use of powerful regressors such as deep neural networks. We then derive a covariance constraint that can be used to automatically lear...

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

Actions


Access Document


Files:
Publisher copy:
10.1007/978-3-319-49409-8_11

Authors


More by this author
Department:
Oxford, MPLS, Engineering Science
More by this author
Department:
Oxford, MPLS, Engineering Science
Publisher:
Springer, Cham Publisher's website
Volume:
9915
Pages:
100-117
Series:
Lecture Notes in Computer Science
Publication date:
2016-11-05
Acceptance date:
2016-08-12
DOI:
ISSN:
0302-9743
Pubs id:
pubs:656431
URN:
uri:37b8b819-83a9-4716-9e7d-68f73150ea9c
UUID:
uuid:37b8b819-83a9-4716-9e7d-68f73150ea9c
Local pid:
pubs:656431
ISBN:
978-3-319-49408-1

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