Multi-expert adversarial regularization for robust and data-efficient deep supervised learning
US12051237B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 17, 2022 |
| Grant date | Jul 30, 2024 |
| Priority date | — |
| Expiry date | Jan 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.