Patents by Inventor Seungyong MOON

Seungyong MOON 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).

  • Publication number: 20240242072
    Abstract: An apparatus and method with out-of-distribution data detection is provided. The apparatus includes one or more processors configured to execute instructions; and one or more memories storing the instructions, wherein, the execution of the instructions by the one or more processors configures the one or more processors to generate output data using a neural network model provided input data; determine, based on the output data, a maximum loss value among calculated loss values that correspond to neighboring data within a reference distance from the input data; and detect, based on the maximum loss value and a threshold, whether the input data is out-of-distribution (OOD) data that is different from in-distribution data corresponding to training data used in a training of the neural network model.
    Type: Application
    Filed: July 27, 2023
    Publication date: July 18, 2024
    Applicants: SAMSUNG ELECTRONICS CO., LTD., Seoul National University R&DB Foundation
    Inventors: Jongseok KIM, Seungyong MOON, Hyun Oh SONG
  • Patent number: 11921818
    Abstract: A method includes obtaining a color transformation matrix that removes color distortion of an original color histogram of a target color space for an input image of an original color space; obtaining a color transformation image of the original color space from which color distortion of the input image is removed using the color transformation matrix; and obtaining a space transformation image with a minimum target loss value between an output vector of a neural network for one of candidate images and each of a plurality of candidate class vectors of the input image, the candidate images being spaced apart from the color transformation image of the original color space by a distance less than a threshold.
    Type: Grant
    Filed: May 26, 2021
    Date of Patent: March 5, 2024
    Assignees: Samsung Electronics Co., Ltd., Seoul National University R&DB Foundation
    Inventors: Jang-Hyun Kim, Hyun Oh Song, Wonho Choo, Seungyong Moon, Gaon An, Hosan Jeong
  • Publication number: 20220171999
    Abstract: A method includes obtaining a color transformation matrix that removes color distortion of an original color histogram of a target color space for an input image of an original color space; obtaining a color transformation image of the original color space from which color distortion of the input image is removed using the color transformation matrix; and obtaining a space transformation image with a minimum target loss value between an output vector of a neural network for one of candidate images and each of a plurality of candidate class vectors of the input image, the candidate images being spaced apart from the color transformation image of the original color space by a distance less than a threshold.
    Type: Application
    Filed: May 26, 2021
    Publication date: June 2, 2022
    Applicants: SAMSUNG ELECTRONICS CO., LTD., Seoul National University R&DB Foundation
    Inventors: Jang-Hyun KIM, Hyun Oh SONG, Wonho CHOO, Seungyong MOON, Gaon AN, Hosan JEONG