Patent · US Active

Few-shot training of a neural network

US11593661B2 · kind B2 · utility

0Cited by
0References
29Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 19, 2019
Grant dateFeb 28, 2023
Priority date
Expiry dateMar 3, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V10/82
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A neural network is trained to identify one or more features of an image. The neural network is trained using a small number of original images, from which a plurality of additional images are derived. The additional images generated by rotating and decoding embeddings of the image in a latent space generated by an autoencoder. The images generated by the rotation and decoding exhibit changes to a feature that is in proportion to the amount of rotation.

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