Patent · US Active

Method for training neural network, system for training neural network, and neural network

US12136230B2 · kind B2 · utility

0Cited by
2References
13Claims
0Family size

Assignees

Inventors

Key dates

Filing dateApr 11, 2022
Grant dateNov 5, 2024
Priority date
Expiry dateMay 12, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/30252
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method for training a first neural network to detect the viewpoint of an object visible on an image and belonging to a given category of object when this image is inputted to the first neural network, including: providing a dataset of pairs of images under different viewpoints, providing a second neural network configured to be able to deliver appearance information of an object, providing a third neural network configured to be able to deliver a synthetic image of an object of the category using appearance information and a viewpoint, jointly training the first neural network, the second neural network, and the third neural network.

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