logo

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 11978272 B1

PDFFull Text
Date of Patent:
May. 07, 2024

Filed:

Aug. 09, 2022

Domain adaptation for machine learning models

Applicant:

Adobe Inc., San Jose, CA (US);

Inventors:

Kai Li, Somerville, MA (US);

Christopher Alan Tensmeyer, Provo, UT (US);

Curtis Michael Wigington, San Jose, CA (US);

Handong Zhao, San Jose, CA (US);

Nikolaos Barmpalios, Sunnyvale, CA (US);

Tong Sun, San Ramon, CA (US);

Varun Manjunatha, College Park, MD (US);

Vlad Ion Morariu, Potomac, MD (US);

Assignee:

Adobe Inc., San Jose, CA (US);

Attorney:

FIG. 1 Patents

Primary Examiner:

Dhaval V Patel

Int. Cl.
CPC ...
G06V 30/413 (2022.01); G06F 17/18 (2006.01); G06F 18/213 (2023.01); G06F 18/2415 (2023.01); G06N 3/047 (2023.01); G06N 3/084 (2023.01); G06N 20/00 (2019.01); G06N 20/10 (2019.01); G06V 10/25 (2022.01); G06V 10/82 (2022.01); G06V 20/20 (2022.01); G06V 30/19 (2022.01); G06V 30/414 (2022.01);
U.S. Cl.
CPC ...
G06V 30/413 (2022.01); G06F 17/18 (2013.01); G06F 18/213 (2023.01); G06F 18/2415 (2023.01); G06N 3/047 (2023.01); G06N 3/084 (2013.01); G06N 20/00 (2019.01); G06N 20/10 (2019.01); G06V 10/25 (2022.01); G06V 10/82 (2022.01); G06V 20/20 (2022.01); G06V 30/19173 (2022.01); G06V 30/414 (2022.01);
Abstract

Adapting a machine learning model to process data that differs from training data used to configure the model for a specified objective is described. A domain adaptation system trains the model to process new domain data that differs from a training data domain by using the model to generate a feature representation for the new domain data, which describes different content types included in the new domain data. The domain adaptation system then generates a probability distribution for each discrete region of the new domain data, which describes a likelihood of the region including different content described by the feature representation. The probability distribution is compared to ground truth information for the new domain data to determine a loss function, which is used to refine model parameters. After determining that model outputs achieve a threshold similarity to the ground truth information, the model is output as a domain-agnostic model.

Find Patent Forward Citations

Loading…