Conference item icon

Conference item

TransMix: attend to mix for Vision Transformers

Abstract:

Mixup-based augmentation has been found to be effective for generalizing models during training, especially for Vision Transformers (ViTs) since they can easily overfit. However, previous mixup-based methods have an underlying prior knowledge that the linearly interpolated ratio of targets should be kept the same as the ratio proposed in input interpolation. This may lead to a strange phenomenon that sometimes there is no valid object in the mixed image due to the random process in augmentati...

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

Actions


Access Document


Files:
Publisher copy:
10.1109/CVPR52688.2022.01182

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More from this funder
Name:
European Commission
Grant:
321162
Publisher:
IEEE
Host title:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Pages:
12125-12134
Publication date:
2022-09-27
Acceptance date:
2022-06-19
Event title:
Conference on Computer Vision and Pattern Recognition (CVPR 2022)
Event location:
New Orleans, Louisiana
Event website:
https://cvpr2022.thecvf.com/
Event start date:
2022-06-19
Event end date:
2022-06-24
DOI:
EISSN:
2575-7075
ISSN:
1063-6919
EISBN:
9781665469463
ISBN:
9781665469470
Language:
English
Keywords:
Pubs id:
1272328
Local pid:
pubs:1272328
Deposit date:
2022-08-03

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