中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.019 seconds)

    SCENE GRAPH GENERATION FOR UNLABELED DATA
    2.
    发明申请
    SCENE GRAPH GENERATION FOR UNLABELED DATA 有权

    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

    IPC: G06K9/62 ,  G06K9/00

    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.

    Scene graph generation for unlabeled data
    3.
    发明授权
    Scene graph generation for unlabeled data 有权

    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

    IPC: G06K9/62 ,  G06V20/00 ,  G06V10/82 ,  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.

    LEARNING TO GENERATE SYNTHETIC DATASETS FOR TRANING NEURAL NETWORKS
    5.
    发明申请
    LEARNING TO GENERATE SYNTHETIC DATASETS FOR TRANING NEURAL NETWORKS 审中-公开

    公开(公告)号：US20200160178A1

    公开(公告)日：2020-05-21

    申请号：US16685795

    申请日：2019-11-15

    Applicant: NVIDIA Corporation

    Inventor： Amlan Kar ,  Aayush Prakash ,  Ming-Yu Liu ,  David Jesus Acuna Marrero ,  Antonio Torralba Barriuso ,  Sanja Fidler

    IPC: G06N3/08 ,  G06F16/901 ,  G06N3/04 ,  G06T11/60

    Abstract: In various examples, a generative model is used to synthesize datasets for use in training a downstream machine learning model to perform an associated task. The synthesized datasets may be generated by sampling a scene graph from a scene grammar—such as a probabilistic grammar—and applying the scene graph to the generative model to compute updated scene graphs more representative of object attribute distributions of real-world datasets. The downstream machine learning model may be validated against a real-world validation dataset, and the performance of the model on the real-world validation dataset may be used as an additional factor in further training or fine-tuning the generative model for generating the synthesized datasets specific to the task of the downstream machine learning model.

    Learning to generate synthetic datasets for training neural networks
    7.
    发明授权
    Learning to generate synthetic datasets for training neural networks 有权

    公开(公告)号：US11610115B2

    公开(公告)日：2023-03-21

    申请号：US16685795

    申请日：2019-11-15

    Applicant: NVIDIA Corporation

    Inventor： Amlan Kar ,  Aayush Prakash ,  Ming-Yu Liu ,  David Jesus Acuna Marrero ,  Antonio Torralba Barriuso ,  Sanja Fidler

    IPC: G06N3/08 ,  G06F16/901 ,  G06T11/60 ,  G06N3/04

    Abstract: In various examples, a generative model is used to synthesize datasets for use in training a downstream machine learning model to perform an associated task. The synthesized datasets may be generated by sampling a scene graph from a scene grammar—such as a probabilistic grammar—and applying the scene graph to the generative model to compute updated scene graphs more representative of object attribute distributions of real-world datasets. The downstream machine learning model may be validated against a real-world validation dataset, and the performance of the model on the real-world validation dataset may be used as an additional factor in further training or fine-tuning the generative model for generating the synthesized datasets specific to the task of the downstream machine learning model.

Patent Agency Ranking