Patents by Inventor Aman Irshad

Aman Irshad 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).

  • Method of training image deep learning model and device thereof
    Patent number: 11720790
    Abstract: Disclosed herein is an image deep learning model training method. The method includes sampling a twin negative comprising a first negative sample and a second negative sample by selecting the first negative sample with a highest similarity out of an anchor sample and a positive sample constituting a matching pair in each class and by selecting the second negative sample with a highest similarity to the first negative sample, and training the samples to minimize a loss of a loss function in each class by utilizing the anchor sample, the positive sample, the first and second negative samples for each class. The first negative sample is selected in a different class from a class comprising the matching pair, and the second negative sample is selected in a different class from classes comprising the matching pair and the first negative sample.
    Type: Grant
    Filed: May 21, 2020
    Date of Patent: August 8, 2023
    Assignees: Electronics and Telecommunications Research Institute, INFORMATION TECHNOLOGY UNIVERSITY (ITU)
    Inventors: Yong Ju Cho, Jeong Il Seo, Rehan Hafiz, Mohsen Ali, Muhammad Faisal, Aman Irshad
  • METHOD OF TRAINING IMAGE DEEP LEARNING MODEL AND DEVICE THEREOF
    Publication number: 20200372350
    Abstract: Disclosed herein is an image deep learning model training method. The method includes sampling a twin negative comprising a first negative sample and a second negative sample by selecting the first negative sample with a highest similarity out of an anchor sample and a positive sample constituting a matching pair in each class and by selecting the second negative sample with a highest similarity to the first negative sample, and training the samples to minimize a loss of a loss function in each class by utilizing the anchor sample, the positive sample, the first and second negative samples for each class. The first negative sample is selected in a different class from a class comprising the matching pair, and the second negative sample is selected in a different class from classes comprising the matching pair and the first negative sample.
    Type: Application
    Filed: May 21, 2020
    Publication date: November 26, 2020
    Applicants: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, NFORMATION TECHNOLOGY UNIVERSITY (ITU)
    Inventors: Yong Ju CHO, Jeong Il SEO, Rehan Hafiz, Mohsen Ali, Muhammad Faisal, Aman Irshad