DEVICES, SYSTEMS, AND METHODS FOR LEARNING A DISCRIMINANT IMAGE REPRESENTATION
First Claim
1. A method comprising:
- obtaining a set of low-level features from an image;
generating a high-dimensional generative representation of the image based on the low-level features;
generating a lower-dimensional representation of the image based on the high-dimensional generative representation of the image;
generating classifier scores based on classifiers and on one or more of the high-dimensional generative representation and the lower-dimensional representation, wherein each classifier uses the one or more of the high-dimensional generative representation and the lower-dimensional representation as an input, and wherein each classifier is associated with a respective category; and
generating a combined representation for the image based on the classifier scores and the lower-dimensional representation.
1 Assignment
0 Petitions
Accused Products
Abstract
Systems, devices, and methods for generating an image representation obtain a set of low-level features from an image; generate a high-dimensional generative representation of the low-level features; generate a lower-dimensional representation of the low-level features based on the high-dimensional generative representation of the low-level features; generate classifier scores based on classifiers and on one or more of the high-dimensional generative representation and the lower-dimensional representation, wherein each classifier uses the one or more of the high-dimensional generative representation and the lower-dimensional representation as an input, and wherein each classifier is associated with a respective label; and generate a combined representation for the image based on the classifier scores and the lower-dimensional representation.
34 Citations
15 Claims
-
1. A method comprising:
-
obtaining a set of low-level features from an image; generating a high-dimensional generative representation of the image based on the low-level features; generating a lower-dimensional representation of the image based on the high-dimensional generative representation of the image; generating classifier scores based on classifiers and on one or more of the high-dimensional generative representation and the lower-dimensional representation, wherein each classifier uses the one or more of the high-dimensional generative representation and the lower-dimensional representation as an input, and wherein each classifier is associated with a respective category; and generating a combined representation for the image based on the classifier scores and the lower-dimensional representation. - View Dependent Claims (2, 3, 4)
-
-
5. A method comprising:
-
generating a high-dimensional generative representation of low-level features of a query image; generating a category classifier score for the query image based on a classifier and on the high-dimensional generative representation of the query image; and generating a comparison score for the query image and the reference image based at least on the high-dimensional generative representation and on the category classifier score. - View Dependent Claims (6, 7, 8, 9, 10, 11, 12)
-
-
13. A method comprising:
-
obtaining a low-level features from images in a set of images, where each image is associated with one or more labels; generating a high-dimensional representation based on the low-level features; generating a lower-dimensional representation based on the high-dimensional representation; generating a respective representation for each of the images in the set of images based on the lower-dimensional representation; and training a respective classifier for each of the one or more labels based on the respective label and on the respective representation of each of the images that are associated with the label. - View Dependent Claims (14, 15)
-
Specification