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