Generating and augmenting transfer learning datasets with pseudo-labeled images
US11151410B2 · kind B2 · utility
0Cited by
2References
17Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Sep 7, 2018 |
| Grant date | Oct 19, 2021 |
| Priority date | — |
| Expiry date | Dec 30, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F18/22
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A computer-implemented method for data labeling is provided. The computer-implemented method assigns pseudo-labels to unlabeled examples of data using a similarity metric on an embedding space to produce pseudo-labeled examples. A curriculum learning model is trained using the pseudo-labeled examples. The curriculum learning model trained with the pseudo-labeled examples is employed in in a fine-tuning task to enhance classification accuracy of the data.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.