中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

16 records (took 0.017 seconds)

    Processing images using deep neural networks
    1.
    发明授权
    Processing images using deep neural networks 有权

    公开(公告)号：US09904875B2

    公开(公告)日：2018-02-27

    申请号：US15649947

    申请日：2017-07-14

    Applicant: Google Inc.

    Inventor： Christian Szegedy ,  Vincent O. Vanhoucke

    IPC: G06K9/46 ,  G06K9/66 ,  G06N3/04 ,  G06N3/08

    CPC classification number: G06K9/66 ,  G06N3/0454 ,  G06N3/063 ,  G06N3/084

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image.

    OBJECT DETECTION USING DEEP NEURAL NETWORKS
    3.
    发明申请
    OBJECT DETECTION USING DEEP NEURAL NETWORKS 有权
    使用深层神经网络的对象检测

    公开(公告)号：US20150170002A1

    公开(公告)日：2015-06-18

    申请号：US14288194

    申请日：2014-05-27

    Applicant: Google Inc.

    Inventor： Christian Szegedy ,  Dumitru Erhan ,  Alexander Toshkov Toshev

    IPC: G06K9/66

    CPC classification number: G06K9/66 ,  G06K9/4628

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting objects in images. One of the methods includes receiving an input image. A full object mask is generated by providing the input image to a first deep neural network object detector that produces a full object mask for an object of a particular object type depicted in the input image. A partial object mask is generated by providing the input image to a second deep neural network object detector that produces a partial object mask for a portion of the object of the particular object type depicted in the input image. A bounding box is determined for the object in the image using the full object mask and the partial object mask.

    Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于检测图像中的对象。 其中一种方法包括接收输入图像。 通过将输入图像提供给产生输入图像中描绘的特定对象类型的对象的完整对象掩模的第一深层神经网络对象检测器来生成完整对象掩码。 通过将输入图像提供给第二深神经网络对象检测器来产生部分对象掩模，该第二深神经网络对象检测器为输入图像中描绘的特定对象类型的对象的一部分产生部分对象掩模。 使用完整对象掩码和部分对象掩码，为图像中的对象确定边框。

    Adversarial training of neural networks
    4.
    发明授权
    Adversarial training of neural networks 有权

    公开(公告)号：US10521718B1

    公开(公告)日：2019-12-31

    申请号：US15279268

    申请日：2016-09-28

    Applicant: Google Inc.

    Inventor： Christian Szegedy ,  Ian Goodfellow

    IPC: G06N3/08 ,  G06N20/00

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for adversarial training of a neural network. One of the methods includes obtaining a plurality of training inputs; and training the neural network on each of the training inputs, comprising, for each of the training inputs: processing the training input using the neural network to determine a neural network output for the training input; applying a perturbation to the training input to generate an adversarial perturbation of the training input; processing the adversarial perturbation of the training input using the neural network to determine a neural network output for the adversarial perturbation; and adjusting the current values of the parameters of the neural network by performing an iteration of a neural network training procedure to optimize an adversarial objective function.

    IMAGE CLASSIFICATION NEURAL NETWORKS
    6.
    发明申请
    IMAGE CLASSIFICATION NEURAL NETWORKS 审中-公开

    公开(公告)号：US20170243085A1

    公开(公告)日：2017-08-24

    申请号：US15395530

    申请日：2016-12-30

    Applicant: Google Inc.

    Inventor： Vincent O. Vanhoucke ,  Christian Szegedy ,  Sergey Ioffe

    IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04

    CPC classification number: G06K9/6267 ,  G06K9/00979 ,  G06K9/4628 ,  G06N3/04 ,  G06N3/0445 ,  G06N3/08

    Abstract: A neural network system that includes: multiple subnetworks that includes: a first subnetwork including multiple first modules, each first module including: a pass-through convolutional layer configured to process the subnetwork input for the first subnetwork to generate a pass-through output; an average pooling stack of neural network layers that collectively processes the subnetwork input for the first subnetwork to generate an average pooling output; a first stack of convolutional neural network layers configured to collectively process the subnetwork input for the first subnetwork to generate a first stack output; a second stack of convolutional neural network layers that are configured to collectively process the subnetwork input for the first subnetwork to generate a second stack output; and a concatenation layer configured to concatenate the pass-through output, the average pooling output, the first stack output, and the second stack output to generate a first module output for the first module.

    Robust and fast model fitting by adaptive sampling
    7.
    发明授权
    Robust and fast model fitting by adaptive sampling 有权
    通过自适应采样的鲁棒快速模型拟合

    公开(公告)号：US09129228B1

    公开(公告)日：2015-09-08

    申请号：US14304143

    申请日：2014-06-13

    Applicant: Google Inc.

    Inventor： Christian Szegedy

    IPC: G06F15/18 ,  G06N99/00

    CPC classification number: G06N99/005

    Abstract: Aspects of the present disclosure relate generally to model fitting. A target model having a large number of inputs is fit using a performance model having relatively few inputs. The performance model is learned during the fitting process. Optimal optimization parameters including a sample size, a damping factor, and an iteration count are selected for an optimization round. A random subset of data is sampled based on the selected sample size. The optimization round is conducted using the iteration count and the sampled data to produce optimized parameters. The performance model is updated based on the performance of the optimization round. The parameters of the target model are then updated based on the damping factor and the parameters computed by the optimization round. The aforementioned steps are performed in a loop in order to obtain optimized parameters and fit of the data to the target model.

    Abstract translation: 本公开的方面通常涉及模型拟合。 具有大量输入的目标模型使用具有相对较少输入的性能模型进行拟合。 性能模型在拟合过程中得到了学习。 选择包括样本大小，阻尼因子和迭代计数的最优优化参数进行优化轮次。 数据的随机子集基于所选择的样本大小进行采样。 使用迭代计数和采样数据进行优化回合，以产生优化的参数。 性能模型根据优化轮次的性能进行更新。 然后基于阻尼因子和由优化轮计算的参数来更新目标模型的参数。 上述步骤在循环中执行，以便获得优化的参数和数据对目标模型的拟合。

    OBJECT DETECTION USING NEURAL NETWORK SYSTEMS
    8.
    发明申请
    OBJECT DETECTION USING NEURAL NETWORK SYSTEMS 审中-公开

    公开(公告)号：US20190019050A1

    公开(公告)日：2019-01-17

    申请号：US15650790

    申请日：2017-07-14

    Applicant: Google Inc.

    Inventor： Dominik Roblek ,  Christian Szegedy ,  Jacek Slawosz Jurewicz

    IPC: G06K9/32 ,  G06N3/08 ,  G06T7/11 ,  G06K9/46 ,  G06K9/66

    CPC classification number: G06K9/3241 ,  G06K9/4628 ,  G06K9/6271 ,  G06K9/66 ,  G06N3/08 ,  G06T7/11

    Abstract: Systems, methods, and apparatus, including computer programs encoded on a computer storage medium. In one aspect, a system includes initial neural network layers configured to: receive an input image, and process the input image to generate a plurality of first feature maps that characterize the input image; a location generating convolutional neural network layer configured to perform a convolution on the representation of the first plurality of feature maps to generate data defining a respective location of each of a predetermined number of bounding boxes in the input image, wherein each bounding box identifies a respective first region of the input image; and a confidence score generating convolutional neural network layer configured to perform a convolution on the representation of the first plurality of feature maps to generate a confidence score for each of the predetermined number of bounding boxes in the input image.

    Training a neural network to detect objects in images
    9.
    发明授权
    Training a neural network to detect objects in images 有权

    公开(公告)号：US09514389B1

    公开(公告)日：2016-12-06

    申请号：US15185613

    申请日：2016-06-17

    Applicant: Google Inc.

    Inventor： Dumitru Erhan ,  Christian Szegedy ,  Dragomir Anguelov

    IPC: G06K9/62 ,  G06K9/66

    CPC classification number: G06K9/6256 ,  G06K9/3241 ,  G06K9/4628 ,  G06K9/6202 ,  G06K9/66 ,  G06N3/0454 ,  G06N3/084

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network to detect object in images. One of the methods includes receiving a training image and object location data for the training image; providing the training image to a neural network and obtaining bounding box data for the training image from the neural network, wherein the bounding box data comprises data defining a plurality of candidate bounding boxes in the training image and a respective confidence score for each candidate bounding box in the training image; determining an optimal set of assignments using the object location data for the training image and the bounding box data for the training image, wherein the optimal set of assignments assigns a respective candidate bounding box to each of the object locations; and training the neural network on the training image using the optimal set of assignments.

Patent Agency Ranking