LABEL-EMBEDDING VIEW OF ATTRIBUTE-BASED RECOGNITION
First Claim
1. A non-transitory storage medium storing instructions readable and executable by an electronic data processing device to perform a method including the operations of:
- representing classes of a set of classes Y={yj, j=1, . . . , C} by class attribute vectors φ
(yj) where φ
is an embedding function that embeds a class in an attribute space of dimensionality E where each dimension ai,i=1, . . . , E of the attribute space corresponds to a class attribute;
representing training images xn of a set of training images S labeled by respective training image class labels yn as θ
(xn) where θ
is an embedding function that embeds an image in an image feature space of dimensionality D;
optimizing respective to the set of training images S a set of parameters w of a prediction function
7 Assignments
0 Petitions
Accused Products
Abstract
In image classification, each class of a set of classes is embedded in an attribute space where each dimension of the attribute space corresponds to a class attribute. The embedding generates a class attribute vector for each class of the set of classes. A set of parameters of a prediction function operating in the attribute space respective to a set of training images annotated with classes of the set of classes is optimized such that the prediction function with the optimized set of parameters optimally predicts the annotated classes for the set of training images. The prediction function with the optimized set of parameters is applied to an input image to generate at least one class label for the input image. The image classification does not include applying a class attribute classifier to the input image.
-
Citations
20 Claims
-
1. A non-transitory storage medium storing instructions readable and executable by an electronic data processing device to perform a method including the operations of:
-
representing classes of a set of classes Y={yj, j=1, . . . , C} by class attribute vectors φ
(yj) where φ
is an embedding function that embeds a class in an attribute space of dimensionality E where each dimension ai,i=1, . . . , E of the attribute space corresponds to a class attribute;representing training images xn of a set of training images S labeled by respective training image class labels yn as θ
(xn) where θ
is an embedding function that embeds an image in an image feature space of dimensionality D;optimizing respective to the set of training images S a set of parameters w of a prediction function - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A method comprising:
-
embedding each class of a set of classes in an attribute space where each dimension of the attribute space corresponds to a class attribute, the embedding generating a class attribute vector for each class of the set of classes; optimizing a set of parameters of a prediction function operating in the attribute space respective to a set of training images annotated with classes of the set of classes such that the prediction function with the optimized set of parameters optimally predicts the annotated classes for the set of training images; and applying the prediction function with the optimized set of parameters to an input image to generate at least one class label for the input image; wherein the method is performed by an electronic data processing device. - View Dependent Claims (11, 12, 13, 14, 15, 16)
-
-
17. An apparatus comprising:
an electronic data processing device programmed to perform a method including the operations of; embedding classes of a set of classes Y={yj, j=1, . . . , C} in an attribute space of dimensionality E where each dimension ai, i=1, . . . , E of the attribute space corresponds to a class attribute; embedding training images xn of a set of training images S labeled by respective training image class labels yn in an image feature space of dimensionality D; optimizing a set of parameters w of a prediction function y=ƒ
(x;
w) operating in the image feature space and in the attribute space respective to the set of training images S wherein x denotes an image and y denotes the predicted class label for the image x; andapplying the prediction function y=ƒ
(x;
w) with the optimized set of parameters w to an input image to generate at least one class label for the input image.- View Dependent Claims (18, 19, 20)
Specification