Patent · US Active

Multi-expert adversarial regularization for robust and data-efficient deep supervised learning

US12051237B2 · kind B2 · utility

0Cited by
8References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 17, 2022
Grant dateJul 30, 2024
Priority date
Expiry dateJan 15, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V10/7784
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A system and a method to train a neural network are disclosed. A first image is weakly and strongly augmented. The first image, the weakly and strongly augmented first images are input into a feature extractor to obtain augmented features. Each weakly augmented first image is input to a corresponding first expert head to determine a supervised loss for each weakly augmented first image. Each strongly augmented first image is input to a corresponding second expert head to determine a diversity loss for each strongly augmented first image. The feature extractor is trained to minimize the supervised loss on weakly augmented first images and to minimize a multi-expert consensus loss on strongly augmented first images. Each first expert head is trained to minimize the supervised loss for each weakly augmented first image, and each second expert head is trained to minimize the diversity loss for each strongly augmented first image.

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