公开(公告)号：US20240211749A1

公开(公告)日：2024-06-27

申请号：US18340996

申请日：2023-06-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sujin JANG ,  Dae Ung JO

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: A method and apparatus with object estimation model training is provided. The method include generating a cross-correlation loss based on a first feature vector, generated using an interim first neural network (NN) model provided an input based on first input data about a target object, and a second feature vector generated using a trained second neural network provided another input based on second input data about the target object; and generating a trained first NN model, including training the interim first NN model based on the cross-correlation loss.

公开(公告)号：US20250086469A1

公开(公告)日：2025-03-13

申请号：US18605119

申请日：2024-03-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Nayeon KIM ,  Sujin JANG ,  Dae Ung JO

IPC: G06N3/09

Abstract: A learning method of generating a vector map and a method and apparatus for generating a vector map are disclosed. The learning method includes converting a first feature extracted by inputting a first modality sensed by a first sensor to a student model into a first feature vector in a bird eye view (BEV) space, converting a second feature extracted by inputting a multi-modality including the first modality and a second modality sensed by a second sensor to a teacher model into a second feature vector in the BEV space, and learning the student model to generate a vector map corresponding to the first modality by back-propagating cross-correlation loss by dimension that causes the first feature vector to replicate a cross-correlation with the second feature vector to the student model.

公开(公告)号：US20250157195A1

公开(公告)日：2025-05-15

申请号：US18897759

申请日：2024-09-26

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  Korea University Research and Business Foundation

Inventor： Sujin JANG ,  Sangpil KIM ,  Jinkyu KIM ,  Won Jeong RYOO ,  Dongwook LEE ,  Gyusam CHANG ,  Dae Hyun JI

IPC: G06V10/774 ,  G06V10/77

Abstract: A processor-implemented method including text-guided training using a pre-trained text-guided model and an image feature extractor based on one or more text inputs and one or more image inputs corresponding to the one or more text inputs, light detection and ranging (LiDAR)-guided training using a point cloud encoder and a bird's-eye view (BEV) encoder, and training an object detection model based on a result of the text-guided training and a result of the LiDAR-guided training, and the text-guided training includes outputting one or more text-image features that are used to train the object detection model by using the text-guided model and the image feature extractor.

公开(公告)号：US20240161442A1

公开(公告)日：2024-05-16

申请号：US18451287

申请日：2023-08-17

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  Korea University Research and Business Foundation

Inventor： Sujin JANG ,  Sangpil KIM ,  Jinkyu KIM ,  Wonseok ROH ,  Gyusam CHANG ,  Dongwook LEE ,  Dae Hyun JI

IPC: G06V10/25 ,  G01S17/86 ,  G01S17/89 ,  G06V10/44 ,  G06V10/74 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06V10/25 ,  G01S17/86 ,  G01S17/89 ,  G06V10/44 ,  G06V10/761 ,  G06V10/764 ,  G06V10/82 ,  G06V2201/07

Abstract: A method and apparatus with object detector training is provided. The method includes obtaining first input data and second input data from a target object; obtaining second additional input data by performing data augmentation on the second input data; extracting a first feature to a shared embedding space by inputting the first input data to a first encoder; extracting a second feature to the shared embedding space by inputting the second input data to a second encoder; extracting a second additional feature to the shared embedding space by inputting thesecond additional input data to the second encoder; identifying a first loss function based on the first feature, the second feature, and the second additional feature; identifying a second loss function based on the second feature and the second additional feature; and updating a weight of the second encoder based on the first loss function and the second loss function.

公开(公告)号：US20250061552A1

公开(公告)日：2025-02-20

申请号：US18934744

申请日：2024-11-01

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sujin JANG ,  Joohan NA ,  Dokwan OH

IPC: G06T5/80 ,  G06N3/088 ,  G06T5/50

Abstract: A processor-implemented method with data processing using a neural network includes: determining a first translated image by translating a first image based on a second image, the first image and a second image that having different distortions, such that a distortion of the first image corresponds to a distortion of the second image; determining a first retranslated image by translating the first translated image such that a distortion of the first translated image corresponds to a distortion of the first image; and training a first deformation field generator configured to determine a first relative deformation field that represents a relative deformation from the first image to the second image and a second deformation field generator configured to determine a second relative deformation field that represents a relative deformation from the second image to the first image, based on a loss between the first retranslated image and the first image.

公开(公告)号：US20230360381A1

公开(公告)日：2023-11-09

申请号：US18109928

申请日：2023-02-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaewoo LEE ,  Yonggonjong PARK ,  Kapje SUNG ,  Sujin JANG

IPC: G06V10/82 ,  G06V10/25 ,  G06V10/24 ,  G01S19/07 ,  G06V10/44

CPC classification number: G06V10/82 ,  G01S19/07 ,  G06V10/242 ,  G06V10/25 ,  G06V10/44 ,  G06V2201/07

Abstract: An apparatus and method with data labeling are provided. An apparatus includes one or more processors configured to obtain localization information related to an object, based on the localization information, extract a landmark point from a landmark map including coordinates of a landmark, generate a ground truth image based on the extracted landmark point, and generate training data by refining the ground truth image.

公开(公告)号：US20220366548A1

公开(公告)日：2022-11-17

申请号：US17575002

申请日：2022-01-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sujin JANG ,  Joohan NA ,  Dokwan OH

IPC: G06T5/00 ,  G06T5/50 ,  G06N3/08

Abstract: A processor-implemented method with data processing using a neural network includes: determining a first translated image by translating a first image based on a second image, the first image and a second image that having different distortions, such that a distortion of the first image corresponds to a distortion of the second image; determining a first retranslated image by translating the first translated image such that a distortion of the first translated image corresponds to a distortion of the first image; and training a first deformation field generator configured to determine a first relative deformation field that represents a relative deformation from the first image to the second image and a second deformation field generator configured to determine a second relative deformation field that represents a relative deformation from the second image to the first image, based on a loss between the first retranslated image and the first image.