Back to results
US 12,189,714 B2Granted
System and method for improved few-shot object detection using a dynamic semantic network
AssigneeCarnegie Mellon University
InventorsMarios Savvides, Chenchen Zhu, Fangyi Chen, Uzair Ahmed, Ran Tao
Life of this patent
Estimating the term…
Abstract
Disclosed herein is an improved few-shot detector which utilizes a dynamic semantic network which takes as input a language feature and generates trainable parameters for a visual network. The visual network takes a visual feature as input and generates a classification and localization of an object.
Claims22
A few-shot object detector comprising:
- a visual network with trainable parameters producing an output based on an input of a visual feature;
- and
- a dynamic semantic network which accepts as input a language feature representing a semantic representation of a class and outputs a class-specific parameter for the visual network;
- wherein the dynamic semantic network includes a dynamic relation graph for building direct connections between base classes and novel classes using non-visual knowledge of the base classes.
1 more element
A method comprising:
- training a visual network with trainable parameters to produce an output based on an input of a visual feature;
- and
- training a dynamic semantic network to accept as input a language feature representing a semantic representation of a class and to output a class-specific parameter for the visual network;
- wherein the dynamic semantic network includes a dynamic relation graph for building direct connections between base classes and novel classes using non-visual knowledge of the base classes.
1 more element
Dependencies are inferred from the claim text.