Conference item icon

Conference item

Gather-excite: Exploiting feature context in convolutional neural networks

Abstract:

While the use of bottom-up local operators in convolutional neural networks (CNNs) matches well some of the statistics of natural images, it may also prevent such models from capturing contextual long-range feature interactions. In this work, we propose a simple, lightweight approach for better context exploitation in CNNs. We do so by introducing a pair of operators: gather, which efficiently aggregates feature responses from a large spatial extent, and excite, which redistributes the pooled...

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

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
New College
Role:
Author
More from this funder
Funding agency for:
Albanie, S
Grant:
CentreforDoctoralTraininginAutonomousIntelligent Machines
Systems
More from this funder
Funding agency for:
Vedaldi, A
Grant:
677195-IDIU
Publisher:
Neural Information Processing Systems (NIPS) Foundation Publisher's website
Journal:
32nd Conference on Neural Information Processing Systems Journal website
Host title:
Advances in Neural Information Processing Systems 31 (NIPS 2018)
Publication date:
2018-12-31
Acceptance date:
2018-09-05
Event location:
Montréal, Canada
Source identifiers:
948559
Pubs id:
pubs:948559
UUID:
uuid:29272d1a-72d7-4689-b388-f960dff864da
Local pid:
pubs:948559
Deposit date:
2018-11-30

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