Patents by Inventor George Trigeorgis

George Trigeorgis has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Domain separation neural networks
    Patent number: 11361531
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using an image processing neural network system. One of the system includes a shared encoder neural network implemented by one or more computers, wherein the shared encoder neural network is configured to: receive an input image from a target domain; and process the input image to generate a shared feature representation of features of the input image that are shared between images from the target domain and images from a source domain different from the target domain; and a classifier neural network implemented by the one or more computers, wherein the classifier neural network is configured to: receive the shared feature representation; and process the shared feature representation to generate a network output for the input image that characterizes the input image.
    Type: Grant
    Filed: April 5, 2021
    Date of Patent: June 14, 2022
    Assignee: Google LLC
    Inventors: Konstantinos Bousmalis, Nathan Silberman, Dilip Krishnan, George Trigeorgis, Dumitru Erhan
  • DOMAIN SEPARATION NEURAL NETWORKS
    Publication number: 20210224573
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using an image processing neural network system. One of the system includes a shared encoder neural network implemented by one or more computers, wherein the shared encoder neural network is configured to: receive an input image from a target domain; and process the input image to generate a shared feature representation of features of the input image that are shared between images from the target domain and images from a source domain different from the target domain; and a classifier neural network implemented by the one or more computers, wherein the classifier neural network is configured to: receive the shared feature representation; and process the shared feature representation to generate a network output for the input image that characterizes the input image.
    Type: Application
    Filed: April 5, 2021
    Publication date: July 22, 2021
    Inventors: Konstantinos Bousmalis, Nathan Silberman, Dilip Krishnan, George Trigeorgis, Dumitru Erhan
  • Domain separation neural networks
    Patent number: 10970589
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using an image processing neural network system. One of the system includes a shared encoder neural network implemented by one or more computers, wherein the shared encoder neural network is configured to: receive an input image from a target domain; and process the input image to generate a shared feature representation of features of the input image that are shared between images from the target domain and images from a source domain different from the target domain; and a classifier neural network implemented by the one or more computers, wherein the classifier neural network is configured to: receive the shared feature representation; and process the shared feature representation to generate a network output for the input image that characterizes the input image.
    Type: Grant
    Filed: July 28, 2016
    Date of Patent: April 6, 2021
    Assignee: Google LLC
    Inventors: Konstantinos Bousmalis, Nathan Silberman, Dilip Krishnan, George Trigeorgis, Dumitru Erhan
  • DOMAIN SEPARATION NEURAL NETWORKS
    Publication number: 20190180136
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using an image processing neural network system. One of the system includes a shared encoder neural network implemented by one or more computers, wherein the shared encoder neural network is configured to: receive an input image from a target domain; and process the input image to generate a shared feature representation of features of the input image that are shared between images from the target domain and images from a source domain different from the target domain; and a classifier neural network implemented by the one or more computers, wherein the classifier neural network is configured to: receive the shared feature representation; and process the shared feature representation to generate a network output for the input image that characterizes the input image.
    Type: Application
    Filed: July 28, 2016
    Publication date: June 13, 2019
    Inventors: Konstantinos Bousmalis, Nathan Silberman, Dilip Krishnan, George Trigeorgis, Dumitru Erhan