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:
Sep. 19, 2023

Filed:

Oct. 30, 2020
Applicant:

Dassault Systemes, Velizy Villacoublay, FR;

Inventors:

Louis Dupont De Dinechin, Velizy Villacoublay, FR;

Asma Rejeb Sfar, Velizy Villacoublay, FR;

Assignee:

DASSAULT SYSTEMES, Velizy Villacoublay, FR;

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06V 10/774 (2022.01); G06N 20/10 (2019.01); G06T 7/70 (2017.01); G06F 18/21 (2023.01); G06F 18/23 (2023.01); G06F 18/28 (2023.01); G06F 18/214 (2023.01); G06V 10/44 (2022.01); G06V 10/24 (2022.01); G06N 3/08 (2023.01);
U.S. Cl.
CPC ...
G06V 10/7753 (2022.01); G06F 18/2155 (2023.01); G06F 18/2185 (2023.01); G06F 18/23 (2023.01); G06F 18/28 (2023.01); G06N 3/08 (2013.01); G06N 20/10 (2019.01); G06T 7/70 (2017.01); G06V 10/245 (2022.01); G06V 10/454 (2022.01);
Abstract

A computer-implemented method of signal processing comprises providing images. The method comprises for each respective one of at least a subset of the images: applying a weakly-supervised learnt function, the weakly-supervised learnt function outputting respective couples each including a respective localization and one or more respective confidence scores, each confidence score representing a probability of instantiation of a respective object category at the respective localization. The method further comprises determining, based on the output of the weakly-supervised learnt function, one or more respective annotations, each annotation including a respective localization and a respective label representing instantiation a respective object category at the respective localization. The method further comprises forming a dataset including pieces of data, each piece of data including a respective image of the subset and at least a part of the one or more annotations determined for the respective image. This improves the field of object detection.


Find Patent Forward Citations

Loading…