-
公开(公告)号：US20190080204A1
公开(公告)日：2019-03-14
申请号：US15704746
申请日：2017-09-14
Applicant: Google Inc.
Inventor： Gerhard Florian Schroff , Wenze Hu
CPC classification number: G06K9/6248 , G06F16/5854 , G06K9/00369 , G06K9/00677 , G06K9/6215 , G06K9/6218 , G06K9/6245 , G06K9/6256 , G06K9/6265
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object detection and representation in images. In one aspect, a method includes detecting occurrences of objects of a particular type in images captured within a first duration of time, and iteratively training an image embedding function to produce as output representations of features of the input images depicting occurrences of objects of the particular type, where similar representations of features are generated for images that depict the same instance of an object of a particular type captured within a specified duration of time, and dissimilar representations of features are generated for images that depict different instances of objects of the particular type.
-
公开(公告)号：US20180053042A1
公开(公告)日：2018-02-22
申请号：US15798074
申请日：2017-10-30
Applicant: Google Inc.
Inventor： James William Philbin , Gerhard Florian Schroff , Dmitry Kalenichenko
CPC classification number: G06K9/00288 , G06K9/4619 , G06K9/6218 , G06K9/6256 , G06K9/6267 , G06K9/66 , G06N3/0454 , G06N3/08 , G06N3/084 , G06T2207/20081 , G06T2207/20084
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating numeric embeddings of images. One of the methods includes obtaining training images; generating a plurality of triplets of training images; and training a neural network on each of the triplets to determine trained values of a plurality of parameters of the neural network, wherein training the neural network comprises, for each of the triplets: processing the anchor image in the triplet using the neural network to generate a numeric embedding of the anchor image; processing the positive image in the triplet using the neural network to generate a numeric embedding of the positive image; processing the negative image in the triplet using the neural network to generate a numeric embedding of the negative image; computing a triplet loss; and adjusting the current values of the parameters of the neural network using the triplet loss.
-
公开(公告)号：US09836641B2
公开(公告)日：2017-12-05
申请号：US14972670
申请日：2015-12-17
Applicant: Google Inc.
Inventor： James William Philbin , Gerhard Florian Schroff , Dmitry Kalenichenko
CPC classification number: G06K9/00288 , G06K9/4619 , G06K9/6218 , G06K9/6256 , G06K9/6267 , G06K9/66 , G06N3/0454 , G06N3/08 , G06N3/084 , G06T2207/20081 , G06T2207/20084
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating numeric embeddings of images. One of the methods includes obtaining training images; generating a plurality of triplets of training images; and training a neural network on each of the triplets to determine trained values of a plurality of parameters of the neural network, wherein training the neural network comprises, for each of the triplets: processing the anchor image in the triplet using the neural network to generate a numeric embedding of the anchor image; processing the positive image in the triplet using the neural network to generate a numeric embedding of the positive image; processing the negative image in the triplet using the neural network to generate a numeric embedding of the negative image; computing a triplet loss; and adjusting the current values of the parameters of the neural network using the triplet loss.
-
公开(公告)号：US20160180151A1
公开(公告)日：2016-06-23
申请号：US14972670
申请日：2015-12-17
Applicant: Google Inc.
Inventor： James William Philbin , Gerhard Florian Schroff , Dmitry Kalenichenko
CPC classification number: G06K9/00288 , G06K9/4619 , G06K9/6218 , G06K9/6256 , G06K9/6267 , G06K9/66 , G06N3/0454 , G06N3/08 , G06N3/084 , G06T2207/20081 , G06T2207/20084
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating numeric embeddings of images. One of the methods includes obtaining training images; generating a plurality of triplets of training images; and training a neural network on each of the triplets to determine trained values of a plurality of parameters of the neural network, wherein training the neural network comprises, for each of the triplets: processing the anchor image in the triplet using the neural network to generate a numeric embedding of the anchor image; processing the positive image in the triplet using the neural network to generate a numeric embedding of the positive image; processing the negative image in the triplet using the neural network to generate a numeric embedding of the negative image; computing a triplet loss; and adjusting the current values of the parameters of the neural network using the triplet loss.
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，用于生成图像的数字嵌入。 其中一种方法包括获取训练图像; 产生训练图像的多个三元组; 并训练每个三元组上的神经网络以确定神经网络的多个参数的训练值，其中对于每个三元组训练神经网络包括：使用神经网络来处理三元组中的锚图像以产生 锚图像的数字嵌入; 使用神经网络处理三重态中的正像，以生成正像的数字嵌入; 使用神经网络处理三联体中的负图像以生成负图像的数字嵌入; 计算三元损失; 并使用三元组损失调整神经网络的参数的当前值。
-
-
-
Search Results
4
records
(took 0.04 seconds)
