Dynamic matrix convolution with channel fusion
US12223412B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 16, 2020 |
| Grant date | Feb 11, 2025 |
| Priority date | — |
| Expiry date | Dec 12, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/70
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A computer device for automatic feature detection comprises a processor, a communication device, and a memory configured to hold instructions executable by the processor to instantiate a dynamic convolution neural network, receive input data via the communication network, and execute the dynamic convolution neural network to automatically detect features in the input data. The dynamic convolution neural network compresses the input data from an input space having a dimensionality equal to a predetermined number of channels into an intermediate space having a dimensionality less than the number of channels. The dynamic convolution neural network dynamically fuses the channels into an intermediate representation within the intermediate space and expands the intermediate representation from the intermediate space to an expanded representation in an output space having a higher dimensionality than the dimensionality of the intermediate space. The features in the input data are automatically detected based on the expanded representation.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.