Conference item icon

Conference item

Inductive visual localisation: Factorised training for superior generalisation

Abstract:

End-to-end training of Recurrent Neural Networks (RNNs) have been successfully applied to numerous problems that require processing sequences, such as image captioning, machine translation, and text recognition. However, RNNs often struggle to generalise to sequences longer than the ones encountered during training. In this work, we propose to optimize neural networks explicitly for induction. The idea is to first decompose the problem in a sequence of inductive steps and then to explicitly t...

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

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Oxford college:
Balliol College
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Oxford college:
New College
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Role:
Author
More from this funder
Grant:
Clarendon Fund scholarship
Publisher:
British Machine Vision Conference Publisher's website
Publication date:
2018-09-03
Acceptance date:
2018-07-06
Pubs id:
pubs:942829
URN:
uri:c110d333-44c3-4e77-ac0b-01259881dc61
UUID:
uuid:c110d333-44c3-4e77-ac0b-01259881dc61
Local pid:
pubs:942829

Terms of use


Metrics


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