Projecting images to a generative model based on gradient-free latent vector determination
US11615292B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 31, 2022 |
| Grant date | Mar 28, 2023 |
| Priority date | — |
| Expiry date | Aug 31, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T11/60
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.