Back to results
US 12,770,059 B2Granted
Scalable wavelet transformer-based feature extraction
AssigneeMicrosoft Technology Licensing, LLC
InventorsQiang Xiao, Haichao Wei, Hideyuki Winston Inada, Chengming Jiang
Life of this patent
Estimating the term…
Abstract
Methods, systems, and apparatuses include receiving digital data. Embedded patches are generated using digital data. A transformed patch is generated by applying a transformer block to an embedded patch. Filtered patches are created for the transformed patch by applying wavelet filters to the transformed patch. A combined patch is created by combining the filtered patches. A set of training data is generated using the combined patch. A trained prediction model is generated by applying a prediction model to the set of training data.
Claims20
A method comprising:
- receiving digital data;
- generating a plurality of embedded patches using the digital data;
- generating a transformed patch by applying a transformer block to an embedded patch of the plurality of embedded patches;
- creating a plurality of filtered patches for the transformed patch by applying a plurality of wavelet filters to the transformed patch, wherein the plurality of filtered patches includes a first filtered patch created by applying a first wavelet filter of the plurality of wavelet filters and a second filtered patch created by applying a second wavelet filter of the plurality of wavelet filters;
- converting the first filtered patch into a filtered probability patch, wherein probability values of the filtered probability patch are proportional to a scale of values of the first filtered patch;
- creating a combined patch by combining the plurality of filtered patches including the filtered probability patch and the second filtered patch;
- generating a set of training data using the combined patch;
- and
- generating a trained prediction model by applying a prediction model to the set of training data.
6 more elements
A system comprising:
- at least one memory device;
- and
- a processing device, operatively coupled with the at least one memory device, to:
- receive digital data;
- generate a plurality of embedded patches using the digital data;
- generate a transformed patch by applying a transformer block to an embedded patch of the plurality of embedded patches;
- create a plurality of filtered patches for the transformed patch by applying a plurality of wavelet filters to the transformed patch, wherein the plurality of filtered patches includes a first filtered patch created by applying a first wavelet filter of the plurality of wavelet filters and a second filtered patch created by applying a second wavelet filter of the plurality of wavelet filters;
- convert the first filtered patch into a filtered probability patch, wherein probability values of the filtered probability patch are proportional to a scale of values of the first filtered patch;
- create a combined patch by combining the plurality of filtered patches including the filtered probability patch and the second filtered patch;
- generate a set of training data using the combined patch;
- and
- generate a trained prediction model by applying a prediction model to the set of training data.
9 more elements
A system comprising:
- at least one memory device;
- and
- a processing device, operatively coupled with the at least one memory device, to:
- receive digital data identified by one or more input classifiers;
- generate a plurality of embedded patches using the digital data;
- generate a transformed patch by applying a transformer block to an embedded patch of the plurality of embedded patches;
- create a plurality of filtered patches for the transformed patch by applying a plurality of wavelet filters to the transformed patch, wherein the plurality of filtered patches includes a first filtered patch created by applying a first wavelet filter of the plurality of wavelet filters and a second filtered patch created by applying a second wavelet filter of the plurality of wavelet filters;
- convert the first filtered patch into a filtered probability patch, wherein probability values of the filtered probability patch are proportional to a scale of values of the first filtered patch;
- create a combined patch by combining the plurality of filtered patches including the filtered probability patch and the second filtered patch;
- generate a set of training data using the combined patch and the one or more input classifiers;
- generate a trained prediction model by applying a prediction model to the set of training data;
- apply the trained prediction model to a set of execution data;
- and
- determine, by the trained prediction model, an output based on the set of execution data, wherein the output comprises one or more output classifiers identifying the set of execution data.
11 more elements
Dependencies are inferred from the claim text.