Interpretability-aware redundancy reduction for vision transformers
US12154307B2 · kind B2 · utility
0Cited by
3References
20Claims
0Family size
Assignees
Inventors
Key dates
| Filing date | Dec 22, 2021 |
| Grant date | Nov 26, 2024 |
| Priority date | — |
| Expiry date | Jan 31, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A sequence of patch tokens representing an image can be received. A network can be trained to learn informative patch tokens and uninformative patch tokens in the sequence of patch tokens, in learning to recognize an object in the image. The sequence of patch tokens can be reduced by removing the uninformative patch tokens from the sequence of patch tokens. The reduced sequence of patch tokens can be input to an attention-based deep learning neural network. The attention-based deep learning neural network can be fine-tuned to recognize the object in the image using the reduced sequence of patch tokens.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.