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.

Date of Patent:
Jan. 03, 2023

Filed:

May. 27, 2020
Applicant:

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

Inventors:

Christopher Tensmeyer, San Jose, CA (US);

Vlad Ion Morariu, Potomac, MD (US);

Varun Manjunatha, San Jose, CA (US);

Tong Sun, San Ramon, CA (US);

Nikolaos Barmpalios, San Jose, CA (US);

Kai Li, San Jose, CA (US);

Handong Zhao, San Jose, CA (US);

Curtis Wigington, San Jose, CA (US);

Assignee:

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

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/00 (2022.01); G06K 9/62 (2022.01); G06N 5/04 (2006.01); G06V 30/40 (2022.01);
U.S. Cl.
CPC ...
G06K 9/6257 (2013.01); G06K 9/628 (2013.01); G06K 9/6232 (2013.01); G06K 9/6262 (2013.01); G06N 5/046 (2013.01); G06V 30/40 (2022.01);
Abstract

A domain alignment technique for cross-domain object detection tasks is introduced. During a preliminary pretraining phase, an object detection model is pretrained to detect objects in images associated with a source domain using a source dataset of images associated with the source domain. After completing the pretraining phase, a domain adaptation phase is performed using the source dataset and a target dataset to adapt the pretrained object detection model to detect objects in images associated with the target domain. The domain adaptation phase may involve the use of various domain alignment modules that, for example, perform multi-scale pixel/path alignment based on input feature maps or perform instance-level alignment based on input region proposals.


Find Patent Forward Citations

Loading…