Journal article icon

Journal article

Visualizing deep convolutional neural networks using natural pre-images

Abstract:

Image representations, from SIFT and bag of visual words to convolutional neural networks (CNNs) are a crucial component of almost all computer vision systems. However, our understanding of them remains limited. In this paper we study several landmark representations, both shallow and deep, by a number of complementary visualization techniques. These visualizations are based on the concept of “natural pre-image”, namely a natural-looking image whose representation has some notable property. W...

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

Actions


Access Document


Files:
Publisher copy:
10.1007/s11263-016-0911-8

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
European Research Council More from this funder
Publisher:
Springer Verlag Publisher's website
Journal:
International Journal of Computer Vision Journal website
Volume:
120
Issue:
3
Pages:
233-255
Publication date:
2016-05-18
Acceptance date:
2016-04-15
DOI:
EISSN:
1573-1405
ISSN:
0920-5691
Keywords:
Pubs id:
pubs:624524
UUID:
uuid:23d4558c-45b6-4c30-9b6a-288a7fef3ab9
Local pid:
pubs:624524
Source identifiers:
624524
Deposit date:
2016-05-27

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