Patent · US Active

Systems and methods for contrastive learning of visual representations

US11354778B2 · kind B2 · utility

4Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 13, 2020
Grant dateJun 7, 2022
Priority date
Expiry dateApr 13, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2210/22
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Provided are systems and methods for contrastive learning of visual representations. In particular, the present disclosure provides systems and methods that leverage particular data augmentation schemes and a learnable nonlinear transformation between the representation and the contrastive loss to provide improved visual representations. In contrast to certain existing techniques, the contrastive self-supervised learning algorithms described herein do not require specialized architectures or a memory bank. Some example implementations of the proposed approaches can be referred to as a simple framework for contrastive learning of representations or “SimCLR.” Further example aspects are described below and provide the following benefits and insights.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.