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:
Oct. 04, 2022

Filed:

Oct. 10, 2019
Applicant:

Uatc, Llc, San Francisco, CA (US);

Inventors:

Raquel Urtasun, Toronto, CA;

Xinkai Wei, Toronto, CA;

Ioan Andrei Barsan, Toronto, CA;

Julieta Martinez Covarrubias, Toronto, CA;

Shenlong Wang, Toronto, CA;

Assignee:

UATC, LLC, Mountain View, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/62 (2022.01); G06N 3/04 (2006.01); G06N 3/08 (2006.01); G06N 20/00 (2019.01); G06V 10/44 (2022.01); G06V 10/50 (2022.01); G06V 30/194 (2022.01);
U.S. Cl.
CPC ...
G06K 9/6232 (2013.01); G06K 9/6256 (2013.01); G06K 9/6262 (2013.01); G06N 3/04 (2013.01); G06N 3/0454 (2013.01); G06N 3/08 (2013.01); G06N 3/084 (2013.01); G06N 20/00 (2019.01); G06V 10/454 (2022.01); G06V 10/507 (2022.01); G06V 30/194 (2022.01);
Abstract

Systems, methods, tangible non-transitory computer-readable media, and devices associated with object localization and generation of compressed feature representations are provided. For example, a computing system can access training data including a source feature representation and a target feature representation. An encoded target feature representation can be generated based on the target feature representation and a machine-learned encoding model. A binarized target feature representation can be generated based on the encoded target feature representation and lossless binarization operations. A reconstructed target feature representation can be generated based on the binarized target feature representation and a machine-learned decoding model. A matching score for the source feature representation and the reconstructed target feature representation can be determined. A loss associated with the matching score can be determined. Parameters of the machine-learned encoding model and the machine-learned decoding model can be adjusted based on the loss.


Find Patent Forward Citations

Loading…