公开(公告)号：US20210271938A1

公开(公告)日：2021-09-02

申请号：US17320424

申请日：2021-05-14

Applicant: Lunit Inc.

Inventor： Jae Hwan Lee

IPC: G06K9/62 ,  G06K9/66 ,  G06N3/08

Abstract: A normalization method for machine learning and an apparatus thereof are provided. The normalization method according to some embodiments of the present disclosure may calculate a value of a normalization parameter for an input image through a normalization model before inputting the input image to a target model and normalize the input image using the calculated value of the normalization parameter. Because the normalization model is updated based on a prediction loss of the target model, the input image can be normalized to an image suitable for a target task, so that stability of the learning and performance of the target model can be improved.

公开(公告)号：US11875257B2

公开(公告)日：2024-01-16

申请号：US17320424

申请日：2021-05-14

Applicant: Lunit Inc.

Inventor： Jae Hwan Lee

IPC: G06N3/08 ,  G06F18/10 ,  G06F18/213 ,  G06V10/77 ,  G06V10/82

CPC classification number: G06N3/08 ,  G06F18/10 ,  G06F18/213 ,  G06V10/7715 ,  G06V10/82

Abstract: A normalization method for machine learning and an apparatus thereof are provided. The normalization method according to some embodiments of the present disclosure may calculate a value of a normalization parameter for an input image through a normalization model before inputting the input image to a target model and normalize the input image using the calculated value of the normalization parameter. Because the normalization model is updated based on a prediction loss of the target model, the input image can be normalized to an image suitable for a target task, so that stability of the learning and performance of the target model can be improved.

公开(公告)号：US11042789B2

公开(公告)日：2021-06-22

申请号：US16535314

申请日：2019-08-08

Applicant: Lunit Inc.

Inventor： Jae Hwan Lee

IPC: G06K9/62 ,  G06K9/66 ,  G06N3/08

Abstract: A normalization method for machine learning and an apparatus thereof are provided. The normalization method according to some embodiments of the present disclosure may calculate a value of a normalization parameter for an input image through a normalization model before inputting the input image to a target model and normalize the input image using the calculated value of the normalization parameter. Because the normalization model is updated based on a prediction loss of the target model, the input image can be normalized to an image suitable for a target task, so that stability of the learning and performance of the target model can be improved.