Systems and methods for domain adaptation
US11625612B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jan 31, 2020 |
| Grant date | Apr 11, 2023 |
| Priority date | — |
| Expiry date | Jun 19, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N5/045
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The domain adaptation problem is addressed by using the predictions of a trained model over both source and target domain to retain the model with the assistance of an auxiliary model and a modified objective function. Inaccuracy in the model's predictions in the target domain is treated as noise and is reduced by using a robust learning framework during retraining, enabling unsupervised training in the target domain. Applications include object detection models, where noise in retraining is reduced by explicitly representing label noise and geometry noise in the objective function and using the ancillary model to inject information about label noise.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.