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:
Jun. 27, 2023

Filed:

Aug. 31, 2020
Applicant:

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

Inventors:

Xuanyuan Tu, Milton, CA;

Sivabalan Manivasagam, Toronto, CA;

Mengye Ren, Toronto, CA;

Ming Liang, Toronto, CA;

Bin Yang, Toronto, CA;

Raquel Urtasun, Toronto, CA;

Assignee:

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

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G01S 17/931 (2020.01); G06N 20/00 (2019.01); G01S 17/89 (2020.01); G01S 17/42 (2006.01); G01S 17/894 (2020.01); G06V 20/56 (2022.01); G06V 20/64 (2022.01); G06F 18/214 (2023.01); G06F 18/21 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01);
U.S. Cl.
CPC ...
G01S 17/89 (2013.01); G01S 17/42 (2013.01); G01S 17/894 (2020.01); G01S 17/931 (2020.01); G06F 18/214 (2023.01); G06F 18/217 (2023.01); G06N 20/00 (2019.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01); G06V 20/64 (2022.01); G06V 2201/07 (2022.01); G06V 2201/08 (2022.01);
Abstract

Systems and methods for training object detection models using adversarial examples are provided. A method includes obtaining a training scene and identifying a target object within the training scene. The method includes obtaining an adversarial object and generating a modified training scene based on the adversarial object, the target object, and the training scene. The modified training scene includes the training scene modified to include the adversarial object placed on the target object. The modified training scene is input to a machine-learned model configured to detect the training object. A detection score is determined based on whether the training object is detected, and the machine-learned model and the parameters of the adversarial object are trained based on the detection output. The machine-learned model is trained to maximize the detection output. The parameters of the adversarial object are trained to minimize the detection output.


Find Patent Forward Citations

Loading…