logo

For the Inventor, By the Inventor

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.:

US 11823480 B1

PDFFull Text
Date of Patent:
Nov. 21, 2023

Filed:

Jun. 02, 2021

Method for training image classification model and apparatus for executing the same

Applicant:

Samsung Sds Co., Ltd., Seoul, KR;

Inventors:

Byoung Jip Kim, Seoul, KR;

Jin Ho Choo, Seoul, KR;

Yeong Dae Kwon, Seoul, KR;

Jin Yeop Chang, Seoul, KR;

Young June Gwon, Seoul, KR;

Seung Jai Min, Seoul, KR;

Assignee:

SAMSUNG SDS CO., LTD., Seoul, KR;

Attorney:

Sughrue Mion, PLLC

Primary Examiner:

Bobbak Safaipour

Int. Cl.
CPC ...
G06V 40/10 (2022.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01); G06F 18/214 (2023.01); G06F 18/2415 (2023.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 10/778 (2022.01); G06V 10/24 (2022.01); G06V 10/772 (2022.01);
U.S. Cl.
CPC ...
G06V 40/103 (2022.01); G06F 18/2148 (2023.01); G06F 18/2155 (2023.01); G06F 18/2415 (2023.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06V 10/242 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 10/7796 (2022.01); G06V 10/772 (2022.01);
Abstract

A method for training an image classification model according to an embodiment includes training a feature extractor and a rotation angle classifier to predict a rotation angle of each of unlabeled first training images, training the image classification model to predict a label and rotation angle of each of labeled second training images, but predict a uniform label even though an actual rotation angle of each of the second training images is changed, generating a pseudo label based on a training image that satisfy a preset condition among unlabeled candidate images, and training the image classification model to predict a rotation angle of each of the third training images, and predict a label of each of the third training images based on the pseudo label, but predict a uniform label even though an actual rotation angle of each of the third training images is changed.

Find Patent Forward Citations

Loading…