Patents by Inventor Guibiao LIAO

Guibiao LIAO 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).

  • Patent number: 12347160
    Abstract: Disclosed is an optimization method for constructing a target detection network. The method includes: obtaining high-quality visual media data, low-quality visual media data corresponding to the high-quality visual media data, and a corresponding true label, extracting a first backbone network side output feature generated by a preset prior network for the high-quality visual media data, and extracting a second backbone network side output feature generated by a preset target detection network to be trained for the low-quality visual media data; constructing a feature correlation loss, a salient target position loss and a salient prediction loss based on the first backbone network side output feature, the second backbone network side output feature, and the true label; and optimizing the preset target detection network to be trained based on the feature correlation loss, the salient target position loss, and the salient prediction loss to obtain the target detection network.
    Type: Grant
    Filed: May 18, 2022
    Date of Patent: July 1, 2025
    Assignee: PEKING UNIVERSITY SHENZHEN GRADUATE SCHOOL
    Inventors: Wei Gao, Guibiao Liao, Ge Li
  • Publication number: 20220375192
    Abstract: Disclosed is an optimization method for constructing a target detection network. The method includes: obtaining high-quality visual media data, low-quality visual media data corresponding to the high-quality visual media data, and a corresponding true label, extracting a first backbone network side output feature generated by a preset prior network for the high-quality visual media data, and extracting a second backbone network side output feature generated by a preset target detection network to be trained for the low-quality visual media data; constructing a feature correlation loss, a salient target position loss and a salient prediction loss based on the first backbone network side output feature, the second backbone network side output feature, and the true label; and optimizing the preset target detection network to be trained based on the feature correlation loss, the salient target position loss, and the salient prediction loss to obtain the target detection network.
    Type: Application
    Filed: May 18, 2022
    Publication date: November 24, 2022
    Applicant: PEKING UNIVERSITY SHENZHEN GRADUATE SCHOOL
    Inventors: Wei GAO, Guibiao LIAO, Ge LI