Training deep neural networks with synthetic images
US11100372B2 · kind B2 · utility
1Cited by
1References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Nov 8, 2019 |
| Grant date | Aug 24, 2021 |
| Priority date | — |
| Expiry date | Dec 2, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present disclosure discloses a system and a method. The system and the method generate, via a deep neural network, a first synthetic image based on a simulated image, generate a segmentation mask based on the synthetic image, compare the segmentation mask with a ground truth mask of the synthetic image, update the deep neural network based on the comparison, and generate, via the updated deep neural network, a second synthetic image based on the simulated image.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.