-
公开(公告)号：US12242964B2
公开(公告)日：2025-03-04
申请号：US18341050
申请日：2023-06-26
Applicant: Samsung Electronics Co., Ltd.
Inventor： Qingfeng Liu , Mostafa El-Khamy , Jungwon Lee , Behnam Babagholami Mohamadabadi
IPC: G06K9/62 , G06F18/2321 , G06F18/2323 , G06F18/2415 , G06F18/2431 , G06F18/25 , G06N3/04 , G06N3/045 , G06N3/08 , G06N5/022 , G06N5/025 , G06V10/772 , G06V10/774 , G06V10/80 , G06V30/19
Abstract: A method and system for training a neural network are provided. The method includes receiving an input image, selecting at least one data augmentation method from a pool of data augmentation methods, generating an augmented image by applying the selected at least one data augmentation method to the input image, and generating a mixed image from the input image and the augmented image.
-
公开(公告)号：US11461998B2
公开(公告)日：2022-10-04
申请号：US16777734
申请日：2020-01-30
Applicant: Samsung Electronics Co., Ltd.
Inventor： Qingfeng Liu , Mostafa El-Khamy , Dongwoon Bai , Jungwon Lee
Abstract: Some aspects of embodiments of the present disclosure relate to using a boundary aware loss function to train a machine learning model for computing semantic segmentation maps from input images. Some aspects of embodiments of the present disclosure relate to deep convolutional neural networks (DCNNs) for computing semantic segmentation maps from input images, where the DCNNs include a box filtering layer configured to box filter input feature maps computed from the input images before supplying box filtered feature maps to an atrous spatial pyramidal pooling (ASPP) layer. Some aspects of embodiments of the present disclosure relate to a selective ASPP layer configured to weight the outputs of an ASPP layer in accordance with attention feature maps.
-
公开(公告)号：US20210174082A1
公开(公告)日：2021-06-10
申请号：US17177720
申请日：2021-02-17
Applicant: Samsung Electronics Co., Ltd.
Inventor： Qingfeng Liu , Mostafa El-Khamy , Rama Mythili Vadali , Tae-ui Kim , Andrea Kang , Dongwoon Bai , Jungwon Lee , Maiyuran Wijay , Jaewon Yoo
Abstract: A method for computing a dominant class of a scene includes: receiving an input image of a scene; generating a segmentation map of the input image, the segmentation map being labeled with a plurality of corresponding classes of a plurality of classes; computing a plurality of area ratios based on the segmentation map, each of the area ratios corresponding to a different class of the plurality of classes of the segmentation map; and outputting a detected dominant class of the scene based on a plurality of ranked labels based on the area ratios.
-
公开(公告)号：US20210089807A1
公开(公告)日：2021-03-25
申请号：US16777734
申请日：2020-01-30
Applicant: Samsung Electronics Co., Ltd.
Inventor： Qingfeng Liu , Mostafa El-Khamy , Dongwoon Bai , Jungwon Lee
Abstract: Some aspects of embodiments of the present disclosure relate to using a boundary aware loss function to train a machine learning model for computing semantic segmentation maps from input images. Some aspects of embodiments of the present disclosure relate to deep convolutional neural networks (DCNNs) for computing semantic segmentation maps from input images, where the DCNNs include a box filtering layer configured to box filter input feature maps computed from the input images before supplying box filtered feature maps to an atrous spatial pyramidal pooling (ASPP) layer. Some aspects of embodiments of the present disclosure relate to a selective ASPP layer configured to weight the outputs of an ASPP layer in accordance with attention feature maps.
-
5.发明公开公开(公告)号：US20230360396A1
公开(公告)日：2023-11-09
申请号：US18223957
申请日：2023-07-19
Applicant: Samsung Electronics Co., Ltd.
Inventor： Qingfeng Liu , Mostafa El-Khamy , Rama Mythili Vadali , Tae-ui Kim , Andrea Kang , Dongwoon Bai , Jungwon Lee , Maiyuran Wijay , Jaewon Yoo
IPC: G06V20/00 , G06V20/10 , G06F18/24 , H04N23/61 , H04N23/667 , G06V10/764 , G06V10/82 , G06V10/26 , G06V10/50
CPC classification number: G06V20/35 , G06V20/10 , G06F18/24 , H04N23/61 , H04N23/667 , G06V10/764 , G06V10/82 , G06V10/26 , G06V10/50
Abstract: A method for computing a dominant class of a scene includes: receiving an input image of a scene; generating a segmentation map of the input image, the segmentation map being labeled with a plurality of corresponding classes of a plurality of classes; computing a plurality of area ratios based on the segmentation map, each of the area ratios corresponding to a different class of the plurality of classes of the segmentation map; and outputting a detected dominant class of the scene based on a plurality of ranked labels based on the area ratios.
-
Patent Agency Ranking
公开(公告)号：US20230123254A1
公开(公告)日：2023-04-20
申请号：US18083081
申请日：2022-12-16
Applicant: Samsung Electronics Co., Ltd.
Inventor： Qingfeng Liu , Mostafa El-Khamy , Rama Mythili Vadali , Tae-ui Kim , Andrea Kang , Dongwoon Bai , Jungwon Lee , Maiyuran Wijay , Jaewon Yoo
IPC: G06V20/10 , G06V10/50 , G06F18/24 , H04N23/61 , H04N23/667
Abstract: A method for computing a dominant class of a scene includes: receiving an input image of a scene; generating a segmentation map of the input image, the segmentation map being labeled with a plurality of corresponding classes of a plurality of classes; computing a plurality of area ratios based on the segmentation map, each of the area ratios corresponding to a different class of the plurality of classes of the segmentation map; and outputting a detected dominant class of the scene based on a plurality of ranked labels based on the area ratios.
-
公开(公告)号：US10929665B2
公开(公告)日：2021-02-23
申请号：US16452052
申请日：2019-06-25
Applicant: Samsung Electronics Co., Ltd.
Inventor： Qingfeng Liu , Mostafa El-Khamy , Rama Mythili Vadali , Tae-Ui Kim , Andrea Kang , Dongwoon Bai , Jungwon Lee , Maiyuran Wijay , Jaewon Yoo
Abstract: A method for computing a dominant class of a scene includes: receiving an input image of a scene; generating a segmentation map of the input image, the segmentation map including a plurality of pixels, each of the pixels being labeled with a corresponding class of a plurality of classes; computing a plurality of area ratios based on the segmentation map, each of the area ratios corresponding to a different class of the plurality of classes of the segmentation map; applying inference to generate a plurality of ranked labels based on the area ratios; and outputting a detected dominant class of the scene based on the plurality of ranked labels.
-
8.发明公开公开(公告)号：US20240362487A1
公开(公告)日：2024-10-31
申请号：US18646660
申请日：2024-04-25
Inventor： Ahmed Roushdy ElKordy , Sara Babakniya , Qingfeng Liu , Mostafa El-Khamy , Yahya Hussain Ezzeldin Essa , Salman Avestimehr
IPC: G06N3/082 , G06N3/0455
CPC classification number: G06N3/082 , G06N3/0455
Abstract: A system and a method are disclosed for tuning parameters of a large language model. The method comprises identifying first weights of a machine learning (ML) model. Second weights are received from a client device. The second weights may be based on updating, by the client device, the first weights. An update matrix may be generated based on the second weights. The update matrix may be decomposed into first decomposition matrices. Singular values that satisfy a criterion may be identified based on the first decomposition matrices. Singular vectors may be identified based on the singular values. Second decomposition matrices may be identified based on the singular vectors. Updates may be received from the client device of third weights associated with the second decomposition matrices. An updated ML model may be generated based on the updates of the third weights. An inference may be generated based on the updated ML model.
-
9.发明公开公开(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
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.
-
10.发明授权公开(公告)号：US12051237B2
公开(公告)日：2024-07-30
申请号：US17674832
申请日：2022-02-17
Applicant: Samsung Electronics Co., Ltd.
Inventor： Behnam Babagholami Mohamadabadi , Qingfeng Liu , Mostafa El-Khamy , Jungwon Lee
IPC: G06V10/82 , G06N5/04 , G06V10/774 , G06V10/776 , G06V10/778
CPC classification number: G06V10/82 , G06N5/04 , G06V10/774 , G06V10/776 , G06V10/7784
Abstract: A system and a method to train a neural network are disclosed. A first image is weakly and strongly augmented. The first image, the weakly and strongly augmented first images are input into a feature extractor to obtain augmented features. Each weakly augmented first image is input to a corresponding first expert head to determine a supervised loss for each weakly augmented first image. Each strongly augmented first image is input to a corresponding second expert head to determine a diversity loss for each strongly augmented first image. The feature extractor is trained to minimize the supervised loss on weakly augmented first images and to minimize a multi-expert consensus loss on strongly augmented first images. Each first expert head is trained to minimize the supervised loss for each weakly augmented first image, and each second expert head is trained to minimize the diversity loss for each strongly augmented first image.
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.015 seconds)
