公开(公告)号：US20210056332A1

公开(公告)日：2021-02-25

申请号：US17089902

申请日：2020-11-05

Applicant: Samsung Electronics Co., Ltd.

Inventor： SeungJu HAN ,  SungUn PARK ,  JaeJoon HAN ,  Jinwoo SON ,  ChangYong SON ,  Minsu KO ,  Jihye KIM ,  Chang Kyu CHOI

IPC: G06K9/00

Abstract: An object recognition apparatus and method are provided. The apparatus includes a processor configured to verify a target image using an object model and based on reference intermediate data extracted by a partial layer of the object model as used in an object recognition of an input image, in response to a failure of a verification of the input image after a success of the object recognition of the input image, and perform an additional verification of the target image in response to the target image being verified in the verifying of the target image.

公开(公告)号：US20190188510A1

公开(公告)日：2019-06-20

申请号：US16176440

申请日：2018-10-31

Applicant: Samsung Electronics Co., Ltd.

Inventor： SeungJu HAN ,  SungUn PARK ,  JaeJoon HAN ,  Jinwoo SON ,  ChangYong SON ,  Minsu KO ,  Jihye KIM ,  Chang Kyu CHOI

IPC: G06K9/00

CPC classification number: G06K9/00906 ,  G06K9/00221 ,  G06K9/00288

Abstract: An object recognition apparatus and method are provided. The apparatus includes a processor configured to verify a target image using an object model and based on reference intermediate data extracted by a partial layer of the object model as used in an object recognition of an input image, in response to a failure of a verification of the input image after a success of the object recognition of the input image, and perform an additional verification of the target image in response to the target image being verified in the verifying of the target image.

公开(公告)号：US20190251436A1

公开(公告)日：2019-08-15

申请号：US16273662

申请日：2019-02-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： ChangYong SON ,  Jinwoo SON ,  Sangil JUNG ,  Chang Kyu CHOI ,  Jae-Joon HAN

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06K9/6217 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/0481 ,  G06N3/063

Abstract: A processing method using a neural network includes generating output maps of a current layer of the neural network by performing a convolution operation between input maps of the current layer and weight kernels of the current layer, determining a lightweight format for the output maps of the current layer based on a distribution of at least a portion of activation data being processed in the neural network, and lightening activation data corresponding to the output maps of the current layer to have a low bit width based on the determined lightweight format.