Conference item icon

Conference item

On compositions of transformations in contrastive self-supervised learning

Abstract:

In the image domain, excellent representations can be learned by inducing invariance to content-preserving transformations via noise contrastive learning. In this paper, we generalize contrastive learning to a wider set of transformations, and their compositions, for which either invariance or distinctiveness is sought. We show that it is not immediately obvious how existing methods such as SimCLR can be extended to do so. Instead, we introduce a number of formal requirements that all contras...

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

Actions


Access Document


Files:
Publisher copy:
10.1109/ICCV48922.2021.00944

Authors


Publisher:
IEEE
Host title:
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV 2021)
Pages:
9557-9567
Publication date:
2022-02-28
Acceptance date:
2021-07-23
Event title:
2021 IEEE/CVF International Conference on Computer Vision (ICCV 2021)
Event location:
Montreal, QC, Canada
Event website:
https://iccv2021.thecvf.com/home
Event start date:
2021-10-10
Event end date:
2021-10-17
DOI:
EISSN:
2380-7504
ISSN:
1550-5499
EISBN:
978-1-6654-2812-5
ISBN:
978-1-6654-2813-2
Language:
English
Keywords:
Pubs id:
1242412
Local pid:
pubs:1242412
Deposit date:
2022-03-04

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