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.
Claims27
A method performed by data processing apparatus, the method comprising:
- 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 a plurality of image triplets and the corresponding sparse feature representation of each image in each image triplet, wherein each image triplet comprises an image, a less relevant image, and a more relevant image, and wherein each image in each image triplet is sampled from the collection of images.
A computer storage medium encoded with a computer program, the program comprising instructions that when executed by data processing apparatus cause the data processing apparatus to perform operations comprising:
- 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 a plurality of image triplets and the corresponding sparse feature representations of each image in each image triplet, wherein the image triplet comprises an image, a less relevant image, and a more relevant image, and wherein each image in each image triplet is sampled from the collection of images.
A system comprising:
- one or more processors configured to perform operations including:
- 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 a plurality of image triplets and the corresponding sparse feature representation of each image in each image triplet, wherein the image triplet comprises an image, a less relevant image, and a more relevant image, and wherein each image in each image triplet is sampled from the collection of images.
Dependencies are inferred from the claim text.