Patent · US Active

Classifying images utilizing generative-discriminative feature representations

US11709915B2 · kind B2 · utility

0Cited by
2References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 26, 2020
Grant dateJul 25, 2023
Priority date
Expiry dateJun 16, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/048
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The present disclosure relates to systems, non-transitory computer-readable media, and methods for classifying an input image utilizing a classification model conditioned by a generative model and/or self-supervision. For example, the disclosed systems can utilize a generative model to generate a reconstructed image from an input image to be classified. In turn, the disclosed systems can combine the reconstructed image with the input image itself. Using the combination of the input image and the reconstructed image, the disclosed systems utilize a classification model to determine a classification for the input image. Furthermore, the disclosed systems can employ self-supervised learning to cause the classification model to learn discriminative features for better classifying images of both known classes and open-set categories.

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