Refining Image Relevance Models

摘要

Methods, systems and apparatus for refining image relevance models. In general, one aspect includes receiving a trained image relevance model that generates relevance measures of content feature values of images to a query, identifying a first threshold number of common content feature values for the set of training images, the common content feature values being identified as a set of content feature values that are each shared by at least a portion of the training images, identifying a subset of the set of training images having a quantity of the common content feature values greater than a second threshold number of content features values, and generating a re-trained image relevance model based on content feature values of the set of training images, wherein content feature values of the subset of training images are weighted higher than content feature values of the training images not in the subset.

主权项

1. A method comprising:
identifying a set of training images previously used to train an image relevance model that generates relevance measures of images to query based on content feature values of the images, the query being a unique set of one or more query terms; determining that at least a given portion of the training images from the set of training images that were used to train the image relevance model each include at least a specified number of matching visual features, and in response to determining that at least a given portion of the training images each include at least the specified number of matching visual features:
identifying, as a subset of the set of training images, training images having at least a threshold portion of the specified number of matching visual features;assigning, to each training image in the subset of the training images, higher weights that exceed a weight assigned to other images from the set of training images that are not in the subset of training images; andgenerating a re-trained image relevance model based on visual features of the set of training images and the higher weights assigned to the training images in the subset of training images that have at least the partial portion of the specified number of matching visual features.