Publication Type

Patent

Version

publishedVersion

Publication Date

8-2022

Abstract

Embodiments described herein provide a contrastive learning mechanism with self - labeling refinement , which iteratively employs the network and data themselves to generate more accurate and informative soft labels for contrastive learning . Specifically , the contrastive learning framework includes a self - labeling refinery module to explicitly generate accurate labels , and a momentum mix - up module to increase similarity between a query and its positive , which in turn implicitly improves label accuracy.

Discipline

Databases and Information Systems | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

US20220269946A1

First Page

1

Last Page

17

Publisher

UP Patent Office

Embargo Period

12-17-2024

Copyright Owner and License

Authors

Additional URL

https://patents.google.com/patent/US20220269946A1/en

Share

COinS