-
公开(公告)号：US11574155B2
公开(公告)日：2023-02-07
申请号：US17226561
申请日：2021-04-09
Applicant: Nvidia Corporation
Inventor： Aayush Prakash , Shoubhik Debnath , Jean-Francois Lafleche , Eric Cameracci , Gavriel State , Marc Teva Law
Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
-
Patent Agency Ranking
公开(公告)号：US20210374489A1
公开(公告)日：2021-12-02
申请号：US17226561
申请日：2021-04-09
Applicant: Nvidia Corporation
Inventor： Aayush Prakash , Shoubhik Debnath , Jean-Francois Lafleche , Eric Cameracci , Gavriel State , Marc Teva Law
Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
-
公开(公告)号：US20240320993A1
公开(公告)日：2024-09-26
申请号：US18673785
申请日：2024-05-24
Applicant: Nvidia Corporation
Inventor： Aayush Prakash , Shoubhik Debnath , Jean-Francois Lafleche , Eric Cameracci , Gavriel State , Marc Teva Law
IPC: G06V20/70 , G06F18/10 , G06F18/20 , G06F18/24 , G06V10/764 , G06V10/82 , G06V10/84 , G06V20/00 , G06V20/56
CPC classification number: G06V20/70 , G06F18/10 , G06F18/24 , G06F18/29 , G06V10/764 , G06V10/82 , G06V10/84 , G06V20/00 , G06V20/56
Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
-
公开(公告)号：US11995883B2
公开(公告)日：2024-05-28
申请号：US18163482
申请日：2023-02-02
Applicant: Nvidia Corporation
Inventor： Aayush Prakash , Shoubhik Debnath , Jean-Francois Lafleche , Eric Cameracci , Gavriel State , Marc Teva Law
IPC: G06V10/82 , G06F18/10 , G06F18/20 , G06F18/24 , G06V10/764 , G06V10/84 , G06V20/00 , G06V20/56 , G06V20/70
CPC classification number: G06V10/82 , G06F18/10 , G06F18/24 , G06F18/29 , G06V10/764 , G06V10/84 , G06V20/00 , G06V20/70 , G06V20/56
Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
-
公开(公告)号：US20230177826A1
公开(公告)日：2023-06-08
申请号：US18163482
申请日：2023-02-02
Applicant: Nvidia Corporation
Inventor： Aayush Prakash , Shoubhik Debnath , Jean-Francois Lafleche , Eric Cameracci , Gavriel State , Marc Teva Law
CPC classification number: G06V10/82 , G06V20/70 , G06F18/10 , G06F18/24 , G06F18/29 , G06V10/764 , G06V10/84 , G06V20/00 , G06V20/56
Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
-
公开(公告)号：US20220012596A1
公开(公告)日：2022-01-13
申请号：US16925085
申请日：2020-07-09
Applicant: NVIDIA Corporation
Inventor： Weili Nie , Tero Tapani Karras , Animesh Garg , Shoubhik Debnath , Anjul Patney , Anima Anandkumar
Abstract: Apparatuses, systems, and techniques used to train one or more neural networks to generate images comprising one or more features. In at least one embodiment, one or more neural networks are trained to determine one or more styles for an input image and then generate features associated with said one or more styles in an output image.
-
-
-
-
-
Search Results
6
records
(took 0.019 seconds)
