Transferable vision transformer for unsupervised domain adaptation
US12067081B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 24, 2021 |
| Grant date | Aug 20, 2024 |
| Priority date | — |
| Expiry date | Dec 10, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method and an apparatus for training a transferable vision transformer (TVT) for unsupervised domain adaption (UDA) in heterogeneous devices are provided. The method includes that a heterogeneous device including one or more graphic processing units (GPUs) loads multiple patches into the TVT which includes a transferability adaption module (TAM). Furthermore, a patch-level domain discriminator in the TAM assigns weights to the multiple patches and determines one or more transferable patches based on the weights. Moreover, the heterogeneous device generates a transferable attention output for an attention module in the TAM based on the one or more transferable patches.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.