IDiyas

For the Inventor, By the Inventor

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.:

US 11907850 B1

PDFFull Text
Date of Patent:
Feb. 20, 2024

Filed:

Nov. 11, 2021

Training image-to-image translation neural networks

Applicant:

Google Llc, Mountain View, CA (US);

Inventors:

Rui Zhang, Beijing, CN;

Jia Li, Alto, CA (US);

Tomas Jon Pfister, Foster City, CA (US);

Assignee:

Google LLC, Mountain View, CA (US);

Attorneys:

Honigman LLP

Brett A. Krueger

Primary Examiner:

Emily C Terrell

Assistant Examiner:

Nathan J Bloom

Int. Cl.
CPC ...
G06N 3/084 (2023.01); G06F 18/214 (2023.01); G06F 18/22 (2023.01); G06F 18/21 (2023.01); G06F 18/2413 (2023.01); G06F 18/2134 (2023.01); G06N 3/045 (2023.01); G06N 3/047 (2023.01); G06V 10/74 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01);
U.S. Cl.
CPC ...
G06N 3/084 (2013.01); G06F 18/214 (2023.01); G06F 18/2148 (2023.01); G06F 18/2193 (2023.01); G06F 18/21347 (2023.01); G06F 18/22 (2023.01); G06F 18/2413 (2023.01); G06N 3/045 (2023.01); G06N 3/047 (2023.01); G06V 10/761 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01);
Abstract

A method includes obtaining a source training dataset that includes a plurality of source training images and obtaining a target training dataset that includes a plurality of target training images. For each source training image, the method includes translating, using the forward generator neural network G, the source training image to a respective translated target image according to current values of forward generator parameters. For each target training image, the method includes translating, using a backward generator neural network F, the target training image to a respective translated source image according to current values of backward generator parameters. The method also includes training the forward generator neural network G jointly with the backward generator neural network F by adjusting the current values of the forward generator parameters and the backward generator parameters to optimize an objective function.

Find Patent Forward Citations

Loading…