Modifying neural networks for synthetic conditional digital content generation utilizing contrastive perceptual loss
US11514632B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 6, 2020 |
| Grant date | Nov 29, 2022 |
| Priority date | — |
| Expiry date | Nov 7, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/094
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize a contrastive perceptual loss to modify neural networks for generating synthetic digital content items. For example, the disclosed systems generate a synthetic digital content item based on a guide input to a generative neural network. The disclosed systems utilize an encoder neural network to generate encoded representations of the synthetic digital content item and a corresponding ground-truth digital content item. Additionally, the disclosed systems sample patches from the encoded representations of the encoded digital content items and then determine a contrastive loss based on the perceptual distances between the patches in the encoded representations. Furthermore, the disclosed systems jointly update the parameters of the generative neural network and the encoder neural network utilizing the contrastive loss.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.