Learning semantic image similarity
AssigneeGoogle Inc.
InventorsGal Chechik, Samy Bengio, Varun Sharma
Life of this patent
Estimating the term…
Abstract
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying similar images. In some implementations, a method is provided that includes receiving a collection of images and data associated with each image in the collection of images; generating a sparse feature representation for each image in the collection of images; and training an image similarity function using image triplets sampled from the collection of images and corresponding sparse feature representations.
Claims20
A method for training an image similarity function, comprising:
- sampling a plurality of image triplets from a plurality of images, where each image triplet (pi, pi+, pi−) includes an image pi, a more relevant image pi+, and a less relevant image pi−, and where each of the images in each image triplet has a corresponding vector representation vi, vi+, vi−;
- and
- training a pairwise similarity function S(pi, pj) using the plurality of image triplets and the corresponding vector representations as training data.
A system comprising:
- a processor;
- and
- non-transitory computer-readable medium coupled to the processor and having instructions stored thereon, which, when executed by the processor, cause the processor to perform operations comprising:
- sampling a plurality of image triplets from a plurality of images, where each image triplet (pi, pi+, pi−) includes an image pi, a more relevant image pi+, and a less relevant image pi−, and where each of the images in each image triplet has a corresponding vector representation vi, vi+, vi−;
- and
- training a pairwise similarity function S(pi, pj) using the plurality of image triplets and the corresponding vector representations as training data.
A non-transitory computer-readable medium having instructions stored thereon, which, when executed by a processor, cause the processor to perform operations comprising:
- sampling a plurality of image triplets from a plurality of images, where each image triplet (pi, pi+, pi−) includes an image pi, a more relevant image pi+, and a less relevant image pi−, and where each of the images in each image triplet has a corresponding vector representation vi, vi+, vi−;
- and
- training a pairwise similarity function S(pi, pj) using the plurality of image triplets and the corresponding vector representations as training data.
Dependencies are inferred from the claim text.