中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

19 records (took 0.015 seconds)

    Shape fusion for image analysis
    1.
    发明授权
    Shape fusion for image analysis 有权

    公开(公告)号：US12141986B2

    公开(公告)日：2024-11-12

    申请号：US18333166

    申请日：2023-06-12

    Applicant: Nvidia Corporation

    Inventor： David Jesus Acuna Marrero ,  Towaki Takikawa ,  Varun Jampani ,  Sanja Fidler

    IPC: G06T7/12 ,  G06F18/25 ,  G06V10/20 ,  G06V10/44 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82 ,  G06V20/56

    Abstract: Various types of image analysis benefit from a multi-stream architecture that allows the analysis to consider shape data. A shape stream can process image data in parallel with a primary stream, where data from layers of a network in the primary stream is provided as input to a network of the shape stream. The shape data can be fused with the primary analysis data to produce more accurate output, such as to produce accurate boundary information when the shape data is used with semantic segmentation data produced by the primary stream. A gate structure can be used to connect the intermediate layers of the primary and shape streams, using higher level activations to gate lower level activations in the shape stream. Such a gate structure can help focus the shape stream on the relevant information and reduces any additional weight of the shape stream.

    TRAINING PERCEPTION MODELS USING SYNTHETIC DATA FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
    3.
    发明申请
    TRAINING PERCEPTION MODELS USING SYNTHETIC DATA FOR AUTONOMOUS SYSTEMS AND APPLICATIONS 有权

    公开(公告)号：US20220391766A1

    公开(公告)日：2022-12-08

    申请号：US17827390

    申请日：2022-05-27

    Applicant: NVIDIA Corporation

    Inventor： David Jesus Acuna Marrero ,  Sanja Fidler ,  Jonah Philion

    IPC: G06N20/00

    Abstract: In various examples, systems and methods are disclosed that use a domain-adaptation theory to minimize the reality gap between simulated and real-world domains for training machine learning models. For example, sampling of spatial priors may be used to generate synthetic data that that more closely matches the diversity of data from the real-world. To train models using this synthetic data that still perform well in the real-world, the systems and methods of the present disclosure may use a discriminator that allows a model to learn domain-invariant representations to minimize the divergence between the virtual world and the real-world in a latent space. As such, the techniques described herein allow for a principled approach to learn neural-invariant representations and a theoretically inspired approach on how to sample data from a simulator that, in combination, allow for training of machine learning models using synthetic data.

    LEARNING TO GENERATE SYNTHETIC DATASETS FOR TRANING NEURAL NETWORKS
    7.
    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.

    SHAPE FUSION FOR IMAGE ANALYSIS
    8.
    发明申请
    SHAPE FUSION FOR IMAGE ANALYSIS 有权

    公开(公告)号：US20250139783A1

    公开(公告)日：2025-05-01

    申请号：US18943472

    申请日：2024-11-11

    Applicant: Nvidia Corporation

    Inventor： David Jesus Acuna Marrero ,  Towaki Takikawa ,  Varun Jampani ,  Sanja Fidler

    IPC: G06T7/12 ,  G06F18/25 ,  G06V10/20 ,  G06V10/44 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82 ,  G06V20/56

    Abstract: Various types of image analysis benefit from a multi-stream architecture that allows the analysis to consider shape data. A shape stream can process image data in parallel with a primary stream, where data from layers of a network in the primary stream is provided as input to a network of the shape stream. The shape data can be fused with the primary analysis data to produce more accurate output, such as to produce accurate boundary information when the shape data is used with semantic segmentation data produced by the primary stream. A gate structure can be used to connect the intermediate layers of the primary and shape streams, using higher level activations to gate lower level activations in the shape stream. Such a gate structure can help focus the shape stream on the relevant information and reduces any additional weight of the shape stream.

    Learning to generate synthetic datasets for training neural networks
    10.
    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