US 9,177,046 B2 · Refining image relevance models

Abstract

Methods, systems and apparatus for refining image relevance models. In general, one aspect of the subject matter described in this specification can be implemented in methods that include re-training an image relevance model by generating a first re-trained model based on content feature values of first images of a first portion of training images in a set of training images, receiving, from the first re-trained model, image relevance scores for second images of a second portion of the set of training images, removing, from the set of training images, some of the second images identified as outlier images for which the image relevance score received from the first re-trained model is below a threshold score, and generating a second re-trained model based on content feature values of the first images of the first portion and the second images of the second portion that remain following removal of the outlier images.

Claims20

Dependent claims

A method comprising:

obtaining a trained image relevance model that generates relevance measures of images to a query;
and
re-training the image relevance model, the re-training comprising:
generating an aggregation of near duplicate images among a set of training images;
associating image selection data of the aggregated near duplicate images with the aggregation of the near duplicate images, the image selection data corresponding to user interactions with the near duplicate images when the near duplicate images were presented as search results;
and
generating a re-trained image relevance model based on content feature values of each image in the aggregation of near duplicate images and the image selection data associated with the aggregation of near duplicate images.

4 more elements

Dependencies are inferred from the claim text.

Refining image relevance models

Life of this patent

Refining image relevance models

Life of this patent

Abstract

Claims20