知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

11 records (took 0.013 seconds)

    Highly efficient convolutional neural networks
    1.
    发明授权
    Highly efficient convolutional neural networks 有权

    公开(公告)号：US11823024B2

    公开(公告)日：2023-11-21

    申请号：US17382503

    申请日：2021-07-22

    Applicant: Google LLC

    Inventor： Andrew Gerald Howard ,  Mark Sandler ,  Liang-Chieh Chen ,  Andrey Zhmoginov ,  Menglong Zhu

    IPC: G06N3/04 ,  G06N3/08 ,  G06N3/045 ,  G06N3/048

    CPC classification number: G06N3/04 ,  G06N3/045 ,  G06N3/08 ,  G06N3/048

    Abstract: The present disclosure provides directed to new, more efficient neural network architectures. As one example, in some implementations, the neural network architectures of the present disclosure can include a linear bottleneck layer positioned structurally prior to and/or after one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. As another example, in some implementations, the neural network architectures of the present disclosure can include one or more inverted residual blocks where the input and output of the inverted residual block are thin bottleneck layers, while an intermediate layer is an expanded representation. For example, the expanded representation can include one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. A residual shortcut connection can exist between the thin bottleneck layers that play a role of an input and output of the inverted residual block.

    Memory-Guided Video Object Detection
    2.
    发明申请
    Memory-Guided Video Object Detection 有权

    公开(公告)号：US20220189170A1

    公开(公告)日：2022-06-16

    申请号：US17432221

    申请日：2019-02-22

    Applicant: Google LLC

    Inventor： Menglong Zhu ,  Mason Liu ,  Marie Charisse White ,  Dmitry Kalenichenko ,  Yinxiao Li

    IPC: G06V20/40 ,  G06V10/70 ,  G06V10/80 ,  G06V10/82 ,  G06V10/94 ,  G06V10/776 ,  G06V10/774

    Abstract: Systems and methods for detecting objects in a video are provided. A method can include inputting a video comprising a plurality of frames into an interleaved object detection model comprising a plurality of feature extractor networks and a shared memory layer. For each of one or more frames, the operations can include selecting one of the plurality of feature extractor networks to analyze the one or more frames, analyzing the one or more frames by the selected feature extractor network to determine one or more features of the one or more frames, determining an updated set of features based at least in part on the one or more features and one or more previously extracted features extracted from a previous frame stored in the shared memory layer, and detecting an object in the one or more frames based at least in part on the updated set of features.

    Highly Efficient Convolutional Neural Networks
    5.
    发明申请
    Highly Efficient Convolutional Neural Networks 审中-公开

    公开(公告)号：US20190147318A1

    公开(公告)日：2019-05-16

    申请号：US15898566

    申请日：2018-02-17

    Applicant: Google LLC

    Inventor： Andrew Gerald Howard ,  Mark Sandler ,  Liang-Chieh Chen ,  Andrey Zhmoginov ,  Menglong Zhu

    IPC: G06N3/04 ,  G06N3/08

    Abstract: The present disclosure provides directed to new, more efficient neural network architectures. As one example, in some implementations, the neural network architectures of the present disclosure can include a linear bottleneck layer positioned structurally prior to and/or after one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. As another example, in some implementations, the neural network architectures of the present disclosure can include one or more inverted residual blocks where the input and output of the inverted residual block are thin bottleneck layers, while an intermediate layer is an expanded representation. For example, the expanded representation can include one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. A residual shortcut connection can exist between the thin bottleneck layers that play a role of an input and output of the inverted residual block.

    Highly Efficient Convolutional Neural Networks
    6.
    发明公开
    Highly Efficient Convolutional Neural Networks 审中-公开

    公开(公告)号：US20240119256A1

    公开(公告)日：2024-04-11

    申请号：US18486534

    申请日：2023-10-13

    Applicant: Google LLC

    Inventor： Andrew Gerald Howard ,  Mark Sandler ,  Liang-Chieh Chen ,  Andrey Zhmoginov ,  Menglong Zhu

    IPC: G06N3/04 ,  G06N3/045 ,  G06N3/08

    CPC classification number: G06N3/04 ,  G06N3/045 ,  G06N3/08 ,  G06N3/048

    Abstract: The present disclosure provides directed to new, more efficient neural network architectures. As one example, in some implementations, the neural network architectures of the present disclosure can include a linear bottleneck layer positioned structurally prior to and/or after one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. As another example, in some implementations, the neural network architectures of the present disclosure can include one or more inverted residual blocks where the input and output of the inverted residual block are thin bottleneck layers, while an intermediate layer is an expanded representation. For example, the expanded representation can include one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. A residual shortcut connection can exist between the thin bottleneck layers that play a role of an input and output of the inverted residual block.

    Highly Efficient Convolutional Neural Networks
    7.
    发明申请
    Highly Efficient Convolutional Neural Networks 有权

    公开(公告)号：US20210350206A1

    公开(公告)日：2021-11-11

    申请号：US17382503

    申请日：2021-07-22

    Applicant: Google LLC

    Inventor： Andrew Gerald Howard ,  Mark Sandler ,  Liang-Chieh Chen ,  Andrey Zhmoginov ,  Menglong Zhu

    IPC: G06N3/04 ,  G06N3/08

    Abstract: The present disclosure provides directed to new, more efficient neural network architectures. As one example, in some implementations, the neural network architectures of the present disclosure can include a linear bottleneck layer positioned structurally prior to and/or after one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. As another example, in some implementations, the neural network architectures of the present disclosure can include one or more inverted residual blocks where the input and output of the inverted residual block are thin bottleneck layers, while an intermediate layer is an expanded representation. For example, the expanded representation can include one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. A residual shortcut connection can exist between the thin bottleneck layers that play a role of an input and output of the inverted residual block.

    OBJECT DETECTION USING SPATIO-TEMPORAL FEATURE MAPS
    8.
    发明申请
    OBJECT DETECTION USING SPATIO-TEMPORAL FEATURE MAPS 审中-公开

    公开(公告)号：US20200034627A1

    公开(公告)日：2020-01-30

    申请号：US16047362

    申请日：2018-07-27

    Applicant: Google LLC

    Inventor： Menglong Zhu ,  Mason Liu

    IPC: G06K9/00 ,  G06N3/04 ,  G06K9/62 ,  G06T7/73

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing object detection. In one aspect, a method includes receiving multiple video frames. The video frames are sequentially processed using an object detection neural network to generate an object detection output for each video frame. The object detection neural network includes a convolutional neural network layer and a recurrent neural network layer. For each video frame after an initial video frame, processing the video frame using the object detection neural network includes generating a spatial feature map for the video frame using the convolutional neural network layer and generating a spatio-temporal feature map for the video frame using the recurrent neural network layer.

    Highly efficient convolutional neural networks
    9.
    发明授权
    Highly efficient convolutional neural networks 有权

    公开(公告)号：US11734545B2

    公开(公告)日：2023-08-22

    申请号：US15898566

    申请日：2018-02-17

    Applicant: Google LLC

    Inventor： Andrew Gerald Howard ,  Mark Sandler ,  Liang-Chieh Chen ,  Andrey Zhmoginov ,  Menglong Zhu

    IPC: G06N3/04 ,  G06N3/08 ,  G06N3/045 ,  G06N3/048

    CPC classification number: G06N3/04 ,  G06N3/045 ,  G06N3/08 ,  G06N3/048

    Abstract: The present disclosure provides directed to new, more efficient neural network architectures. As one example, in some implementations, the neural network architectures of the present disclosure can include a linear bottleneck layer positioned structurally prior to and/or after one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. As another example, in some implementations, the neural network architectures of the present disclosure can include one or more inverted residual blocks where the input and output of the inverted residual block are thin bottleneck layers, while an intermediate layer is an expanded representation. For example, the expanded representation can include one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. A residual shortcut connection can exist between the thin bottleneck layers that play a role of an input and output of the inverted residual block.

    Efficient convolutional neural networks and techniques to reduce associated computational costs
    10.
    发明授权
    Efficient convolutional neural networks and techniques to reduce associated computational costs 有权

    公开(公告)号：US11157815B2

    公开(公告)日：2021-10-26

    申请号：US16524410

    申请日：2019-07-29

    Applicant: Google LLC

    Inventor： Andrew Gerald Howard ,  Bo Chen ,  Dmitry Kalenichenko ,  Tobias Christoph Weyand ,  Menglong Zhu ,  Marco Andreetto ,  Weijun Wang

    IPC: G06N3/08 ,  G06N3/04

    Abstract: The present disclosure provides systems and methods to reduce computational costs associated with convolutional neural networks. In addition, the present disclosure provides a class of efficient models termed “MobileNets” for mobile and embedded vision applications. MobileNets are based on a straight-forward architecture that uses depthwise separable convolutions to build light weight deep neural networks. The present disclosure further provides two global hyper-parameters that efficiently trade-off between latency and accuracy. These hyper-parameters allow the entity building the model to select the appropriately sized model for the particular application based on the constraints of the problem. MobileNets and associated computational cost reduction techniques are effective across a wide range of applications and use cases.

Patent Agency Ranking