公开(公告)号：US12026627B2

公开(公告)日：2024-07-02

申请号：US17889883

申请日：2022-08-17

Applicant: Samsung Electronics Co., Ltd.

Inventor： Haoyu Ren ,  Mostafa El-Khamy ,  Jungwon Lee ,  Aman Raj

IPC: G06N3/088 ,  G06F18/21 ,  G06N7/01 ,  G06N20/00 ,  G06T7/11 ,  G06T7/593 ,  G06T15/00 ,  G06V10/82

CPC classification number: G06N3/088 ,  G06F18/21 ,  G06N7/01 ,  G06N20/00 ,  G06T7/11 ,  G06T7/593 ,  G06T15/00 ,  G06V10/82 ,  G06T2200/08 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20132

Abstract: A computer vision (CV) training system, includes: a supervised learning system to estimate a supervision output from one or more input images according to a target CV application, and to determine a supervised loss according to the supervision output and a ground-truth of the supervision output; an unsupervised learning system to determine an unsupervised loss according to the supervision output and the one or more input images; a weakly supervised learning system to determine a weakly supervised loss according to the supervision output and a weak label corresponding to the one or more input images; and a joint optimizer to concurrently optimize the supervised loss, the unsupervised loss, and the weakly supervised loss.

公开(公告)号：US20230260247A1

公开(公告)日：2023-08-17

申请号：US17868660

申请日：2022-07-19

Applicant: Samsung Electronics Co., Ltd.

Inventor： Qingfeng Liu ,  Mostafa El-Khamy

IPC: G06V10/52 ,  G06T7/11 ,  G06V10/26 ,  G06V10/77

CPC classification number: G06V10/52 ,  G06T7/11 ,  G06V10/26 ,  G06V10/7715

Abstract: A computer vision system including: one or more processors; and memory including instructions that, when executed by the one or more processors, cause the one or more processors to: determine a semantic multi-scale context feature and an instance multi-scale context feature of an input scene; generate a joint attention map based on the semantic multi-scale context feature and the instance multi-scale context feature; refine the semantic multi-scale context feature and instance multi-scale context feature based on the joint attention map; and generate a panoptic segmentation image based on the refined semantic multi-scale context feature and the refined instance multi-scale context feature.

公开(公告)号：US20230139004A1

公开(公告)日：2023-05-04

申请号：US17656037

申请日：2022-03-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Andrea D. Kang ,  Jinhong Wu ,  Mostafa El-Khamy

IPC: G06V30/148 ,  G06V30/162 ,  G06V30/18 ,  G06V10/34

Abstract: A method includes receiving a binary annotation of source text; performing a close operation on the binary annotation to generate a closed annotation using an initial kernel size; defining one or more contours in the closed annotation using one or more bounding boxes, respectively; determining a subset of the one or more contours for which a percentage of area occupied by text within a corresponding bounding box exceeds a threshold; and generating a final annotation of the source text based on the subset of the one or more contours.

公开(公告)号：US11620555B2

公开(公告)日：2023-04-04

申请号：US16373913

申请日：2019-04-03

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jongha Ryu ,  Yoo Jin Choi ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G06N7/00 ,  G06N20/00 ,  G06N5/04

Abstract: A method and system are herein disclosed. The method includes developing a joint latent variable model having a first variable, a second variable, and a joint latent variable representing common information between the first and second variables, generating a variational posterior of the joint latent variable model, training the variational posterior, and performing inference of the first variable from the second variable based on the variational posterior.

公开(公告)号：US11423312B2

公开(公告)日：2022-08-23

申请号：US16141035

申请日：2018-09-25

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoo Jin Choi ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G06N3/08 ,  G06F17/15 ,  G06F7/02 ,  G06N3/04

Abstract: A method and system for constructing a convolutional neural network (CNN) model are herein disclosed. The method includes regularizing spatial domain weights, providing quantization of the spatial domain weights, pruning small or zero weights in a spatial domain, fine-tuning a quantization codebook, compressing a quantization output from the quantization codebook, and decompressing the spatial domain weights and using either sparse spatial domain convolution and sparse Winograd convolution after pruning Winograd-domain weights.

公开(公告)号：US20220058507A1

公开(公告)日：2022-02-24

申请号：US17179964

申请日：2021-02-19

Applicant: Samsung Electronics Co., Ltd.

Inventor： Mostafa El-Khamy ,  Weituo Hao ,  Jungwon Lee

IPC: G06N7/00 ,  G06N20/00 ,  H04L29/08

Abstract: Methods and devices are provided for performing federated learning. A global model is distributed from a server to a plurality of client devices. At each of the plurality of client devices: model inversion is performed on the global model to generate synthetic data; the global model is on an augmented dataset of collected data and the synthetic data to generate a respective client model; and the respective client model is transmitted to the server. At the server: client models are received from the plurality of client devices, where each client model is received from a respective client device of the plurality of client devices: model inversion is performed on each client model to generate a synthetic dataset; the client models are averaged to generate an averaged model; and the averaged model is trained using the synthetic dataset to generate an updated model.

公开(公告)号：US11195093B2

公开(公告)日：2021-12-07

申请号：US15867303

申请日：2018-01-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jaeyoung Kim ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G06N3/08 ,  G06N7/00 ,  G06N3/04

Abstract: An apparatus, a method, a method of manufacturing and apparatus, and a method of constructing an integrated circuit are provided. The apparatus includes a teacher network; a student network; a plurality of knowledge bridges between the teacher network and the student network, where each of the plurality of knowledge bridges provides a hint about a function being learned, and where a hint includes a mean square error or a probability; and a loss function device connected to the plurality of knowledge bridges and the student network. The method includes training a teacher network; providing hints to a student network by a plurality of knowledge bridges between the teacher network and the student network; and determining a loss function from outputs of the plurality of knowledge bridges and the student network.

公开(公告)号：US11094072B2

公开(公告)日：2021-08-17

申请号：US16574770

申请日：2019-09-18

Applicant: Samsung Electronics Co., Ltd.

Inventor： Haoyu Ren ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G06T7/50 ,  G06N3/04 ,  G06K9/62

Abstract: A method and system for determining depth information of an image are herein provided. According to one embodiment, the method includes receiving an image input, classifying the input image into a depth range of a plurality of depth ranges, and determining a depth map of the image by applying depth estimation based on the depth range into which the input image is classified.

公开(公告)号：US11043976B2

公开(公告)日：2021-06-22

申请号：US16272653

申请日：2019-02-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： Mostafa El-Khamy ,  Jinhong Wu ,  Jungwon Lee ,  Inyup Kang

IPC: H03M13/00 ,  H03M13/39 ,  G06F11/10 ,  G11B20/18 ,  H03M13/37 ,  H03M13/45

Abstract: A method, system, and non-transitory computer-readable recording medium of decoding a signal are provided. The method includes receiving signal to be decoded, where signal includes at least one symbol; decoding signal in stages, where each at least one symbol of signal is decoded into at least one bit per stage, wherein Log-Likelihood Ratio (LLR) and a path metric are determined for each possible path for each at least one bit at each stage; determining magnitudes of the LLRs; identifying K bits of the signal with smallest corresponding LLR magnitudes; identifying, for each of the K bits, L possible paths with largest path metrics at each decoder stage for a user-definable number of decoder stages; performing forward and backward traces, for each of the L possible paths, to determine candidate codewords; performing a Cyclic Redundancy Check (CRC) on the candidate codewords; and stopping after a first candidate codeword passes the CRC.

公开(公告)号：US10970820B2

公开(公告)日：2021-04-06

申请号：US16693146

申请日：2019-11-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Mostafa El-Khamy ,  Jungwon Lee ,  Haoyu Ren

IPC: G06T3/40 ,  G06N3/04 ,  G06N3/08 ,  G06F9/455

Abstract: In a method for super resolution imaging, the method includes: receiving, by a processor, a low resolution image; generating, by the processor, an intermediate high resolution image having an improved resolution compared to the low resolution image; generating, by the processor, a final high resolution image based on the intermediate high resolution image and the low resolution image; and transmitting, by the processor, the final high resolution image to a display device for display thereby.