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:
Jan. 14, 2025
Filed:
Jan. 28, 2022
Applicant:
Salesforce, Inc., San Francisco, CA (US);
Inventors:
Mingfei Gao, Sunnyvale, CA (US);
Chen Xing, Palo Alto, CA (US);
Assignee:
Salesforce, Inc., San Francisco, CA (US);
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06V 20/62 (2022.01); G06F 40/126 (2020.01); G06T 1/60 (2006.01); G06T 9/00 (2006.01); G06V 10/22 (2022.01); G06V 10/77 (2022.01); G06V 10/774 (2022.01);
U.S. Cl.
CPC ...
G06V 20/635 (2022.01); G06F 40/126 (2020.01); G06T 1/60 (2013.01); G06T 9/00 (2013.01); G06V 10/225 (2022.01); G06V 10/7715 (2022.01); G06V 10/7747 (2022.01);
Abstract
Embodiments described herein provide methods and systems for open vocabulary object detection of images. given a pre-trained vision-language model and an image-caption pair, an activation map may be computed in the image that corresponds to an object of interest mentioned in the caption. The activation map is then converted into a pseudo bounding-box label for the corresponding object category. The open vocabulary detector is then directly supervised by these pseudo box-labels, which enables training object detectors with no human-provided bounding-box annotations.