公开(公告)号：US20240242365A1

公开(公告)日：2024-07-18

申请号：US18415839

申请日：2024-01-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Yi ZHOU ,  Seungin PARK ,  Byung In YOO ,  Sangil JUNG ,  Hui ZHANG

IPC: G06T7/50 ,  G06V10/44 ,  G06V10/74 ,  G06V10/80

CPC classification number: G06T7/50 ,  G06V10/44 ,  G06V10/761 ,  G06V10/806

Abstract: A processor-implemented method including generating a depth-aware feature of an image dependent on image features extracted from image data of the image and generating image data, representing information corresponding to one or more segmentations of the image, based on the depth-aware feature and a depth-aware representation, the depth-aware representation being depth-related information and visual-related information for the image.

公开(公告)号：US20210201447A1

公开(公告)日：2021-07-01

申请号：US17019657

申请日：2020-09-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sangil JUNG ,  Dongwook LEE ,  Jinwoo SON ,  Changyong SON ,  Jaehyoung YOO ,  Seohyung LEE ,  Changin CHOI ,  Jaejoon HAN

IPC: G06T3/40 ,  G06K9/00 ,  G06K9/62

Abstract: A system includes: an image sensor configured to acquire an image; an image processor configured to generate a quantized image based on the acquired image using a trained quantization filter; and an output interface configured to output the quantized image.

公开(公告)号：US20250104259A1

公开(公告)日：2025-03-27

申请号：US18631836

申请日：2024-04-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyeongseok SON ,  Seungin PARK ,  Byung In YOO ,  Dongwook LEE ,  Sangil JUNG

IPC: G06T7/50 ,  G06T5/20 ,  G06T7/12

Abstract: A method performed by one or more processors of an electronic device includes: processing an input image and point cloud data corresponding to the input image; projecting the point cloud data to generate a first depth map and adding new depth values to the first depth map based on the input image; obtaining a second depth map by inputting the input image to a depth estimation model configured to infer depth maps from input images; and training the depth estimation model based on a loss difference between the first depth map and the second depth map.

公开(公告)号：US20230102335A1

公开(公告)日：2023-03-30

申请号：US17722858

申请日：2022-04-18

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seungin PARK ,  Sangil JUNG ,  Byung In YOO

IPC: G06N3/04 ,  G06K9/62

Abstract: A method with dynamic convolution includes: determining kernel adaptation weights corresponding to weight matrices in a category set represented by a plurality of predetermined discrete values; determining a unified kernel based on the weight matrices and the kernel adaptation weights corresponding to the weight matrices; and performing a convolution operation based on the unified kernel.

公开(公告)号：US20210397946A1

公开(公告)日：2021-12-23

申请号：US17111870

申请日：2020-12-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Changin CHOI ,  Changyong SON ,  Seohyung LEE ,  Sangil JUNG

IPC: G06N3/08 ,  G06N3/063 ,  G06K9/62

Abstract: A processor-implemented neural network data processing method includes: determining a total number of either one of a first feature value and values less than or equal to the first feature value, in feature data output from a layer of a neural network; determining a quantization parameter based on the determined number; quantizing the feature data based on the determined quantization parameter; and inputting the quantized feature data to a another layer of the neural network connected to the layer.

公开(公告)号：US20250086953A1

公开(公告)日：2025-03-13

申请号：US18883424

申请日：2024-09-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Xiaoshuai HAO ,  Yi ZHOU ,  Byung In YOO ,  Hui ZHANG ,  Seungin PARK ,  Sangil JUNG

IPC: G06V10/80 ,  G01S17/86 ,  G01S17/89 ,  G06V10/44

Abstract: An image processing method is provided. The method includes obtaining a first bird's eye view (BEV) feature of first data, obtaining a second BEV feature of second data, inputting the first BEV feature and the second BEV feature to a self-attention network to obtain a third BEV feature of the first data and a fourth BEV feature of the second data, and obtaining a fusion feature in which the third BEV feature and the fourth BEV feature are fused, wherein the first data and the second data are collected by different sensors. Related operations of the examples provided by the present disclosure are implemented by an AI model. AI-related functions are performed by non-volatile memory, volatile memory, and a processor.

公开(公告)号：US20240221170A1

公开(公告)日：2024-07-04

申请号：US18471450

申请日：2023-09-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Solae LEE ,  Seungin PARK ,  Hyeongseok SON ,  Byung In YOO ,  Sangil JUNG

IPC: G06T7/149

CPC classification number: G06T7/149 ,  G06T2207/20081

Abstract: An apparatus with image segmentation includes: one or more processors configured to: obtain a second image based on a first segmentation label corresponding to a first image; generate a composite image by composing an image of an object corresponding to an object class of the first image among objects comprised by the second image with the first image; and train an image segmentation model based on the composite image, the first image, and the second image.

公开(公告)号：US20230282024A1

公开(公告)日：2023-09-07

申请号：US18197265

申请日：2023-05-15

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seohyung LEE ,  Jaehyoung YOO ,  Jinwoo SON ,  Changyong SON ,  Sangil JUNG ,  Changin CHOI

IPC: G06V40/16

CPC classification number: G06V40/161

Abstract: Disclosed is a method and apparatus for face detection using an adaptive threshold. The method includes determining a detection box in an input image, calculating a confidence score indicating whether an object in the detection box corresponds to a face, setting an adaptive threshold based on a size of the detection box, and determining whether the object in the detection box corresponds to a face based on comparing the confidence score to the adaptive threshold.

公开(公告)号：US20220019895A1

公开(公告)日：2022-01-20

申请号：US17124791

申请日：2020-12-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jinwoo SON ,  Sangil JUNG ,  Changyong SON ,  Dongwook LEE

IPC: G06N3/08 ,  G06N3/10 ,  G06F17/15

Abstract: A processor-implemented neural network method includes: obtaining a first weight kernel of a weight model and pruning information of the first weight kernel; determining, based on the pruning information, a processing range of an input feature map for each weight element vector of the first weight kernel; performing a convolution operation between the input feature map and the first weight kernel based on the determined processing range; and generating an output feature map of a neural network layer based on an operation result of the convolution operation.

公开(公告)号：US20210365792A1

公开(公告)日：2021-11-25

申请号：US17328124

申请日：2021-05-24

Applicant: Samsung Electronics Co., Ltd. ,  Korea Advanced Institute of Science and Technology

Inventor： Sangil JUNG ,  Sung Ju HWANG ,  Changin CHOI ,  Changyong SON

IPC: G06N3/08 ,  G06N5/04 ,  G06N3/10

Abstract: Disclosed are a neural network-based training method, inference method and apparatus. The neural network-based inference method includes receiving a quantization level for quantizing a weight of a neural network and an activation value that is processed by the neural network, receiving a weight quantized based on the quantization level, generating a quantized activation value by quantizing the activation value based on the quantization level, and performing inference based on the quantized weight and the quantized activation value.