公开(公告)号：US11687781B2

公开(公告)日：2023-06-27

申请号：US17308440

申请日：2021-05-05

Applicant: SEE-OUT PTY LTD

Inventor： Sandra Mau ,  Sabesan Sivapalan

IPC: G06N3/08 ,  G06F16/55 ,  G06F16/583 ,  G06F18/214 ,  G06F18/25 ,  G06F18/2415 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V10/44 ,  G06V20/70 ,  G06V20/10

CPC classification number: G06N3/08 ,  G06F16/55 ,  G06F16/583 ,  G06F18/2155 ,  G06F18/2415 ,  G06F18/254 ,  G06V10/454 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V20/10 ,  G06V20/70

Abstract: A method of training an image classification model includes obtaining training images associated with labels, where two or more labels of the labels are associated with each of the training images and where each label of the two or more labels corresponds to an image classification class. The method further includes classifying training images into one or more classes using a deep convolutional neural network, and comparing the classification of the training images against labels associated with the training images. The method also includes updating parameters of the deep convolutional neural network based on the comparison of the classification of the training images against the labels associated with the training images.

公开(公告)号：US11074478B2

公开(公告)日：2021-07-27

申请号：US16074399

申请日：2017-02-01

Applicant: SEE-OUT PTY LTD.

Inventor： Sandra Mau ,  Sabesan Sivapalan

IPC: G06K9/62 ,  G06F16/55 ,  G06F16/583 ,  G06N3/08

Abstract: A method of training an image classification model includes obtaining training images associated with labels, where two or more labels of the labels are associated with each of the training images and where each label of the two or more labels corresponds to an image classification class. The method further includes classifying training images into one or more classes using a deep convolutional neural network, and comparing the classification of the training images against labels associated with the training images. The method also includes updating parameters of the deep convolutional neural network based on the comparison of the classification of the training images against the labels associated with the training images.