发明名称 |
Method and system for optimizing accuracy-specificity trade-offs in large scale visual recognition |
摘要 |
As visual recognition scales up to ever larger numbers of categories, maintaining high accuracy is increasingly difficult. Embodiment of the present invention include methods for optimizing accuracy-specificity trade-offs in large scale recognition where object categories form a semantic hierarchy consisting of many levels of abstraction. |
申请公布号 |
US9158965(B2) |
申请公布日期 |
2015.10.13 |
申请号 |
US201313831833 |
申请日期 |
2013.03.15 |
申请人 |
The Board of Trustees of the Leland Stanford Junior University |
发明人 |
Li Fei-Fei;Deng Jia;Krause Jonathan;Berg Alexander C. |
分类号 |
G06K9/00;G06K9/62 |
主分类号 |
G06K9/00 |
代理机构 |
KPPB LLP |
代理人 |
KPPB LLP |
主权项 |
1. A method for classifying images, comprising:
receiving an input image to classify using a computer system; scoring a likelihood of each individual node in a plurality of nodes of a classifier using a computer system, where the classifier includes a semantic hierarchy in which the plurality of nodes correspond to a hierarchy of named entities and a set of individual object classifiers to classify a likelihood that the input image contains a named entity in one of a plurality of leaf nodes from the plurality of nodes, where the plurality of leaf nodes correspond to a set of mutually exclusive named entities in the hierarchy of named entities; selecting an individual node from the plurality of nodes most descriptive of the image using a computer system, where the individual node is determined by:
iteratively estimating a reward weight within the classifier that achieves a predetermined accuracy, where the accuracy of the classifier is determined by classifying a validation data set using the estimated reward weight;determining reward weighted likelihoods using the estimated reward weight that achieves the predetermined accuracy; andselecting as the individual node most descriptive of the image the individual node within the plurality of nodes in the semantic hierarchy that has the highest reward weighted likelihood; classifying the input image as a named entity corresponding to the individual node most descriptive of the image using a computer system; and returning the named entity as a classification of the input image using a computer system. |
地址 |
Stanford CA US |