Lightweight transformer for high resolution images
US11983239B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 8, 2021 |
| Grant date | May 14, 2024 |
| Priority date | — |
| Expiry date | May 4, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/806
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods for obtaining attention features are described. Some examples may include: receiving, at a projector of a transformer, a plurality of tokens associated with image features of a first dimensional space; generating, at the projector of the transformer, projected features by concatenating the plurality of tokens with a positional map, the projected features having a second dimensional space that is less than the first dimensional space; receiving, at an encoder of the transformer, the projected features and generating encoded representations of the projected features using self-attention; decoding, at a decoder of the transformer, the encoded representations and obtaining a decoded output; and projecting the decoded output to the first dimensional space and adding the image features of the first dimensional space to obtain attention features associated with the image features.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.