公开(公告)号：US20180137406A1

公开(公告)日：2018-05-17

申请号：US15707064

申请日：2017-09-18

Applicant: Google Inc.

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

IPC: G06N3/04 ,  G06N3/08 ,  G06T7/32

CPC classification number: G06N3/04 ,  G06N3/0454 ,  G06N3/082 ,  G06N3/084 ,  G06T7/32 ,  G06T2207/20081 ,  G06T2207/20084

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.

公开(公告)号：US20150170004A1

公开(公告)日：2015-06-18

申请号：US14449262

申请日：2014-08-01

Applicant: Google Inc.

Inventor： Yang Song ,  Charles J. Rosenberg ,  Andrew Yan-Tak Ng ,  Bo Chen

IPC: G06K9/68 ,  G06K9/62 ,  G06K9/46

CPC classification number: G06K9/68 ,  G06K9/46 ,  G06K9/623 ,  G06K9/6267

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for creating an image similarity model. In one aspect, a method includes obtaining feature vectors for images in a set of images, and determining first similarity measures for unlabeled images relative to a reference image. The first similarity measures are independent of first similarity feedback between the unlabeled images and the reference image. The unlabeled images are ranked based on the first similarity measures, and a weighted feature vector is generated based, in part, on the ranking. Second similarity measures are determined, independent of second similarity feedback, for labeled images and a second reference image. The labeled images are ranked based on the second similarity measures. The weighted feature vector is adjusted based, in part, on a comparison of the ranking to a second ranking of the labeled images that is based on the second similarity feedback.

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，用于创建图像相似性模型。 一方面，一种方法包括获得一组图像中的图像的特征向量，以及确定相对于参考图像的未标记图像的第一相似性度量。 第一相似性度量与未标记图像和参考图像之间的第一相似性反馈无关。 基于第一相似性度量对未标记的图像进行排序，并且部分地基于排名生成加权特征向量。 对于标记图像和第二参考图像，确定与第二相似性反馈无关的第二相似性度量。 基于第二相似性度量对标记图像进行排序。 部分地基于基于第二相似性反馈的标记图像的排名与第二排名的比较来调整加权特征向量。

公开(公告)号：US11157814B2

公开(公告)日：2021-10-26

申请号：US15707064

申请日：2017-09-18

Applicant: Google Inc.

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.

公开(公告)号：US09275310B2

公开(公告)日：2016-03-01

申请号：US14449262

申请日：2014-08-01

Applicant: Google Inc.

Inventor： Yang Song ,  Charles J. Rosenberg ,  Andrew Yan-Tak Ng ,  Bo Chen

IPC: G06K9/68 ,  G06K9/62 ,  G06K9/46

CPC classification number: G06K9/68 ,  G06K9/46 ,  G06K9/623 ,  G06K9/6267

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for creating an image similarity model. In one aspect, a method includes obtaining feature vectors for images in a set of images, and determining first similarity measures for unlabeled images relative to a reference image. The first similarity measures are independent of first similarity feedback between the unlabeled images and the reference image. The unlabeled images are ranked based on the first similarity measures, and a weighted feature vector is generated based, in part, on the ranking. Second similarity measures are determined, independent of second similarity feedback, for labeled images and a second reference image. The labeled images are ranked based on the second similarity measures. The weighted feature vector is adjusted based, in part, on a comparison of the ranking to a second ranking of the labeled images that is based on the second similarity feedback.

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，用于创建图像相似性模型。 一方面，一种方法包括获得一组图像中的图像的特征向量，以及确定相对于参考图像的未标记图像的第一相似性度量。 第一相似性度量与未标记图像和参考图像之间的第一相似性反馈无关。 基于第一相似性度量对未标记的图像进行排序，并且部分地基于排名生成加权特征向量。 对于标记图像和第二参考图像，确定与第二相似性反馈无关的第二相似性度量。 基于第二相似性度量对标记图像进行排序。 部分地基于基于第二相似性反馈的标记图像的排名与第二排名的比较来调整加权特征向量。