Classifying digital images in few-shot tasks based on neural networks trained using manifold mixup regularization and self-supervision
US11308353B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 23, 2019 |
| Grant date | Apr 19, 2022 |
| Priority date | — |
| Expiry date | Jul 10, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/82
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present disclosure relates to systems, methods, and non-transitory computer readable media for training a classification neural network to classify digital images in few-shot tasks based on self-supervision and manifold mixup. For example, the disclosed systems can train a feature extractor as part of a base neural network utilizing self-supervision and manifold mixup. Indeed, the disclosed systems can apply manifold mixup regularization over a feature manifold learned via self-supervised training such as rotation training or exemplar training. Based on training the feature extractor, the disclosed systems can also train a classifier to classify digital images into novel classes not present within the base classes used to train the feature extractor.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.