Back to results
US 10,706,324 B2Granted
Multi-view embedding with soft-max based compatibility function for zero-shot learning
AssigneeHRL Laboratories, LLC
InventorsXi Hang Cao, Kyungnam Kim
Life of this patent
Estimating the term…
Abstract
Described is a system for multi-view embedding for object recognition. During operation, the system receives an input image and transforms raw data of objects in the image with corresponding labels into low-level features and high-level semantic representations of the labels. A trained object recognition model is generated by embedding the low-level features with multiple high-level semantic representations. The system then receives data of an unknown object and assigns a label to the unknown object using the trained object recognition model. Finally, a device can be controlled based on the label.
Claims23
A system for multi-view embedding, the system comprising:
- one or more processors and a memory, the memory being a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions, the one or more processors perform operations of:
- transforming raw data of objects with corresponding labels into low-level features and high-level semantic representations of the labels;
- and
- generating a trained object recognition model by embedding the low-level features with multiple high-level semantic representations;
- receiving data of an unknown object and assigning a label to the unknown object using the trained object recognition model, wherein a soft-max formulation provides a confidence of each possible classification outcome, and the assignment of the label to the unknown object is based on the soft-max formulation;
- and
- controlling a device based on the label.
4 more elements
A computer program product for multi-view embedding, the computer program product comprising:
- a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions by one or more processors, the one or more processors perform operations of:
- transforming raw data of objects with corresponding labels into low-level features and high-level semantic representations of the labels;
- and
- generating a trained object recognition model by embedding the low-level features with multiple high-level semantic representations;
- receiving data of an unknown object and assigning a label to the unknown object using the trained object recognition model, wherein a soft-max formulation provides a confidence of each possible classification outcome, and the assignment of the label to the unknown object is based on the soft-max formulation;
- and
- controlling a device based on the label.
4 more elements
A computer implemented method for multi-view embedding, the method comprising an act of:
- causing one or more processors to execute instructions encoded on a non-transitory computer-readable medium, such that upon execution, the one or more processors perform operations of:
- transforming raw data of objects with corresponding labels into low-level features and high-level semantic representations of the labels;
- and
- embedding the low-level features with multiple high-level semantic representations to generate a trained object recognition model;
- receiving data of an unknown object and assigning a label to the unknown object, wherein a soft-max formulation provides a confidence of each possible classification outcome, and the assignment of the label to the unknown object is based on the soft-max formulation;
- and
- controlling a device based on the label.
4 more elements
A system for multi-view embedding, the system comprising:
- one or more processors and a memory, the memory being a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions, the one or more processors perform operations of:
- transforming raw data of objects with corresponding labels into low-level features and high-level semantic representations of the labels;
- and
- generate a trained object recognition model by embedding the low-level features with multiple high-level semantic representations;
- receiving data of an unknown object and assigning a label to the unknown object using the trained object recognition model, wherein a soft-max function is used to provide a degree of compatibility of a pattern's low-level features and corresponding high-level semantic representations, and the assignment of the label to the unknown object is based on the soft-max formulation;
- and
- controlling a device based on the label.
4 more elements
A computer program product for multi-view embedding, the computer program product comprising:
- a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions by one or more processors, the one or more processors perform operations of:
- transforming raw data of objects with corresponding labels into low-level features and high-level semantic representations of the labels;
- and
- generate a trained object recognition model by embedding the low-level features with multiple high-level semantic representations;
- receiving data of an unknown object and assigning a label to the unknown object using the trained object recognition model, wherein a soft-max function is used to provide a degree of compatibility of a pattern's low-level features and corresponding high-level semantic representations, and the assignment of the label to the unknown object is based on the soft-max formulation;
- and
- controlling a device based on the label.
4 more elements
A computer implemented method for multi-view embedding, the method comprising an act of:
- causing one or more processors to execute instructions encoded on a non-transitory computer-readable medium, such that upon execution, the one or more processors perform operations of:
- transforming raw data of objects with corresponding labels into low-level features and high-level semantic representations of the labels;
- and
- embedding the low-level features with multiple high-level semantic representations to generate a trained object recognition model;
- receiving data of an unknown object and assigning a label to the unknown object, wherein a soft-max function is used to provide a degree of compatibility of a pattern's low-level features and corresponding high-level semantic representations, and the assignment of the label to the unknown object is based on the soft-max formulation;
- and
- controlling a device based on the label.
4 more elements
Dependencies are inferred from the claim text.