公开(公告)号：US20170243082A1

公开(公告)日：2017-08-24

申请号：US15504870

申请日：2015-06-19

Applicant: Google Inc.

Inventor： Yang Song ,  Jiang Wang ,  Charles J. Rosenberg

IPC: G06K9/62 ,  G06F17/30 ,  G06N99/00 ,  G06K9/66

CPC classification number: G06K9/6215 ,  G06F17/30256 ,  G06F17/3028 ,  G06K9/6212 ,  G06K9/627 ,  G06K9/66 ,  G06N3/0454 ,  G06N99/005

Abstract: Methods, systems, and apparatus, for determining fine-grained image similarity. In one aspect, a method includes training an image embedding function on image triplets by selecting image triplets of first, second and third images; generating, by the image embedding function, a first, second and third representations of the features of the first, second and third images; determining, based on the first representation of features and the second representation of features, a first similarity measure for the first image to the second image; determining, based on the first representation of features and the third representation of features, a second similarity measure for the first image to the third image; determining, based on the first and second similarity measures, a performance measure of the image embedding function for the image triplet; and adjusting the parameter weights of the image embedding function based on the performance measures for the image triplets.