-
公开(公告)号：US20220391632A1
公开(公告)日：2022-12-08
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
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.
-
2.发明申请公开(公告)号：US20190139205A1
公开(公告)日：2019-05-09
申请号：US15946531
申请日：2018-04-05
Applicant: Samsung Electronics Co., Ltd.
Inventor： Mostafa El-Khamy , Haoyu Ren , Jungwon Lee
Abstract: A method and an apparatus are provided. The method includes receiving a video with a first plurality of frames having a first resolution; generating a plurality of warped frames from the first plurality of frames based on a first type of motion compensation; generating a second plurality of frames having a second resolution, wherein the second resolution is of higher resolution than the first resolution, wherein each of the second plurality of frames having the second resolution is derived from a subset of the plurality of warped frames using a convolutional network; and generating a third plurality of frames having the second resolution based on a second type of motion compensation, wherein each of the third plurality of frames having the second resolution is derived from a fusing a subset of the second plurality of frames.
-
公开(公告)号：US11527005B2
公开(公告)日：2022-12-13
申请号：US16841618
申请日：2020-04-06
Applicant: Samsung Electronics Co., Ltd.
Inventor： Haoyu Ren , Mostafa El-Khamy , Jungwon Lee
Abstract: A method of depth detection based on a plurality of video frames includes receiving a plurality of input frames including a first input frame, a second input frame, and a third input frame respectively corresponding to different capture times, convolving the first to third input frames to generate a first feature map, a second feature map, and a third feature map corresponding to the different capture times, calculating a temporal attention map based on the first to third feature maps, the temporal attention map including a plurality of weights corresponding to different pairs of feature maps from among the first to third feature maps, each weight of the plurality of weights indicating a similarity level of a corresponding pair of feature maps, and applying the temporal attention map to the first to third feature maps to generate a feature map with temporal attention.
-
公开(公告)号：US11055866B2
公开(公告)日：2021-07-06
申请号：US16365167
申请日：2019-03-26
Applicant: Samsung Electronics Co., Ltd.
Inventor： Mostafa El-Khamy , Xianzhi Du , Haoyu Ren , Jungwon Lee
IPC: G06T7/593 , H04N13/239 , G06T3/40 , H04N13/243 , H04N13/133 , H04N13/00
Abstract: An electronic device and method are herein disclosed. The electronic device includes a first camera with a first field of view (FOV), a second camera with a second FOV that is narrower than the first FOV, and a processor configured to capture a first image with the first camera, the first image having a union FOV, capture a second image with the second camera, determine an overlapping FOV between the first image and the second image, generate a disparity estimate based on the overlapping FOV, generate a union FOV disparity estimate, and merge the union FOV disparity estimate with the overlapping FOV disparity estimate.
-
公开(公告)号：US20210124985A1
公开(公告)日：2021-04-29
申请号：US16872199
申请日：2020-05-11
Applicant: Samsung Electronics Co., Ltd.
Inventor： Haoyu Ren , Mostafa El-Khamy , Jungwon Lee , Aman Raj
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.
-
Patent Agency Ranking
公开(公告)号：US11900234B2
公开(公告)日：2024-02-13
申请号：US17007739
申请日：2020-08-31
Applicant: Samsung Electronics Co., Ltd.
Inventor： Haoyu Ren , Mostafa El-Khamy , Jungwon Lee
Abstract: Apparatuses and methods of manufacturing same, systems, and methods for generating a convolutional neural network (CNN) are described. In one aspect, a minimal CNN having, e.g., three or more layers is trained. Cascade training may be performed on the trained CNN to insert one or more intermediate layers until a training error is less than a threshold. When cascade training is complete, cascade network trimming of the CNN output from the cascade training may be performed to improve computational efficiency. To further reduce network parameters, convolutional filters may be replaced with dilated convolutional filters with the same receptive field, followed by additional training/fine-tuning.
-
公开(公告)号：US11699070B2
公开(公告)日：2023-07-11
申请号：US16452005
申请日：2019-06-25
Applicant: Samsung Electronics Co., Ltd.
Inventor： Mostafa El-Khamy , Jungwon Lee , Yoo Jin Choi , Haoyu Ren
CPC classification number: G06N3/08 , G06F18/214 , G06N20/10 , G06V10/454 , G06V10/462 , G06V10/82
Abstract: A method and apparatus for providing a rotational invariant neural network is herein disclosed. According to one embodiment, a method includes receiving a first input of an image in a first orientation and training a kernel to be symmetric such that an output corresponding to the first input is the same as an output corresponding to a second input of the image in a second orientation.
-
公开(公告)号：US11354577B2
公开(公告)日：2022-06-07
申请号：US16138279
申请日：2018-09-21
Applicant: Samsung Electronics Co., Ltd.
Inventor： Haoyu Ren , Mostafa El-Khamy , Jungwon Lee
Abstract: Apparatuses and methods of manufacturing same, systems, and methods are described. In one aspect, a method includes generating a convolutional neural network (CNN) by training a CNN having three or more convolutional layers, and performing cascade training on the trained CNN. The cascade training includes an iterative process of one or more stages, in which each stage includes inserting a residual block (ResBlock) including at least two additional convolutional layers and training the CNN with the inserted ResBlock.
-
公开(公告)号：US20210224953A1
公开(公告)日：2021-07-22
申请号：US17223991
申请日：2021-04-06
Applicant: Samsung Electronics Co., Ltd.
Inventor： Mostafa El-Khamy , Jungwon Lee , Haoyu Ren
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.
-
公开(公告)号：US10803378B2
公开(公告)日：2020-10-13
申请号：US15655557
申请日：2017-07-20
Applicant: Samsung Electronics Co., Ltd.
Inventor： Haoyu Ren , Mostafa El-Khamy , Jungwon Lee
Abstract: Apparatuses and methods of manufacturing same, systems, and methods for generating a convolutional neural network (CNN) are described. In one aspect, a minimal CNN having, e.g., three or more layers is trained. Cascade training may be performed on the trained CNN to insert one or more intermediate layers until a training error is less than a threshold. When cascade training is complete, cascade network trimming of the CNN output from the cascade training may be performed to improve computational efficiency. To further reduce network parameters, convolutional filters may be replaced with dilated convolutional filters with the same receptive field, followed by additional training/fine-tuning.
-
-
-
-
-
-
-
-
-
Search Results
26
records
(took 0.025 seconds)
