Few-shot digital image generation using gan-to-gan translation
US11763495B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jan 29, 2021 |
| Grant date | Sep 19, 2023 |
| Priority date | — |
| Expiry date | Oct 8, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/048
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and efficiently modifying a generative adversarial neural network using few-shot adaptation to generate digital images corresponding to a target domain while maintaining diversity of a source domain and realism of the target domain. In particular, the disclosed systems utilize a generative adversarial neural network with parameters learned from a large source domain. The disclosed systems preserve relative similarities and differences between digital images in the source domain using a cross-domain distance consistency loss. In addition, the disclosed systems utilize an anchor-based strategy to encourage different levels or measures of realism over digital images generated from latent vectors in different regions of a latent space.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.