Electronics and Telecommunications Research Institute

Information Technology University (itu)

Aman Irshad

Jeong Il Seo

Yong Ju Cho

Rehan Hafiz

Muhammad Faisal

Mohsen Ali

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.

Growing community of inventors

Lahore, Pakistan

Aman Irshad