Patent · US Active

Data augmentation method, learning device, and recording medium

US12412374B2 · kind B2 · utility

0Cited by
4References
7Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 1, 2023
Grant dateSep 9, 2025
Priority date
Expiry dateApr 1, 2044

Classification

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

Abstract

First optimization processing for optimizing parameters of a DNN and second optimization processing for optimizing hyperpararneters for each sample used in data augmentation processing are alternately performed. The first optimization processing includes causing the DNN to predict a first augmentation label from a first augmented sample, calculating a first error function between the first augmentation label and a first correct label for a first sample, and updating the parameters in accordance with the first error function. The second optimization processing includes acquiring a second sample, causing the DNN after the updating of the parameters to predict a second label from the second sample, calculating a second error function between the second label and a second correct label for the second sample, and updating the hyperparameter in accordance with a gradient obtained by differentiation of the second error function with respect to the hyperparameter.

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