Conference item icon

Conference item

Cross pixel optical-flow similarity for self-supervised learning

Abstract:

We propose a novel method for learning convolutional neural image representations without manual supervision. We use motion cues in the form of optical-flow, to supervise representations of static images. The obvious approach of training a network to predict flow from a single image can be needlessly difficult due to intrinsic ambiguities in this prediction task. We instead propose a much simpler learning goal: embed pixels such that the similarity between their embeddings matches that betwee...

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

Actions


Access Document


Files:
Publisher copy:
10.1007/978-3-030-20873-8_7

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
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Oxford college:
New College
Publisher:
Springer, Cham Publisher's website
Volume:
11363
Pages:
99-116
Series:
Lecture Notes in Computer Science
Publication date:
2019-05-26
Acceptance date:
2018-09-21
DOI:
ISSN:
0302-9743
Pubs id:
pubs:950914
URN:
uri:8b92a26b-50b9-4a60-a507-1f716c362a51
UUID:
uuid:8b92a26b-50b9-4a60-a507-1f716c362a51
Local pid:
pubs:950914
ISBN:
978-3-030-20893-6

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