Supervised contrastive learning with multiple positive examples
US11347975B2 · kind B2 · utility
0Cited by
3References
18Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Apr 21, 2021 |
| Grant date | May 31, 2022 |
| Priority date | — |
| Expiry date | Apr 21, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting. Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.