The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.
The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.
Patent No.:
Date of Patent:
Jul. 14, 2020
Filed:
Mar. 07, 2019
Applicant:
SK Telecom Co., Ltd., Seoul, KR;
Inventors:
Assignee:
SK TELECOM CO., LTD., Seoul, KR;
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/40 (2006.01); G06F 16/532 (2019.01); G06T 7/246 (2017.01); G06T 1/20 (2006.01); G06T 1/00 (2006.01); G06F 16/51 (2019.01); G06T 11/00 (2006.01); G06N 3/02 (2006.01); G06N 3/04 (2006.01); G06N 3/08 (2006.01);
U.S. Cl.
CPC ...
G06F 16/532 (2019.01); G06F 16/51 (2019.01); G06N 3/02 (2013.01); G06T 1/0007 (2013.01); G06T 1/20 (2013.01); G06T 7/248 (2017.01); G06T 11/00 (2013.01); G06N 3/0454 (2013.01); G06N 3/0472 (2013.01); G06N 3/08 (2013.01);
Abstract
A generative adversarial networks-based or GAN-based method for learning cross-domain relations is disclosed. A provided architecture includes two coupled GANs: a first GAN learning a translation of images from domain A to domain B, and a second GAN learning a translation of images from domain B to domain A. A loop formed by the first GAN and the second GAN causes sample images to be reconstructed into an original domain after being translated into a target domain. Therefore, loss functions representing reconstruction losses of the images may be used to train generative models.