Ranking approach to train deep neural nets for multilabel image annotation
First Claim
1. A method performed by one or more computers, the method comprising:
- receiving respective label scores determined by a neural network for each of at least two labels for at least one training example, wherein at least one of the at least two labels for each training example is a positive label for the training example and at least one other of the at least two labels for each training example is a negative label for the training example;
determining an error of the neural network based on a semantic ranking loss of the label scores, wherein the semantic ranking loss is determined according to;
2 Assignments
0 Petitions
Accused Products
Abstract
Systems and techniques are provided for a ranking approach to train deep neural nets for multilabel image annotation. Label scores may be received for labels determined by a neural network for training examples. Each label may be a positive label or a negative label for the training example. An error of the neural network may be determined based on a comparison, for each of the training examples, of the label scores for positive labels and negative labels for the training example and a semantic distance between each positive label and each negative label for the training example. Updated weights may be determined for the neural network based on a gradient of the determined error of the neural network. The updated weights may be applied to the neural network to train the neural network.
50 Citations
19 Claims
-
1. A method performed by one or more computers, the method comprising:
-
receiving respective label scores determined by a neural network for each of at least two labels for at least one training example, wherein at least one of the at least two labels for each training example is a positive label for the training example and at least one other of the at least two labels for each training example is a negative label for the training example; determining an error of the neural network based on a semantic ranking loss of the label scores, wherein the semantic ranking loss is determined according to; - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A system for a ranking approach to training deep neural networks for multilabel image annotation, comprising:
-
one or more computers; storage coupled to the one or more computers on which is stored a training data set including training examples, a label corpus, and a semantic structure; and a machine learning system deployed on the one or more computers, the machine learning system comprising a neural network and a neural network trainer, the neural network adapted to receive the label corpus and training examples from the training data set, generate respective label scores for each of at least two labels in the label corpus for at least one training example from the training data set, and receive updated weights, and the neural network trainer adapted to determine an error of the neural network based on a semantic ranking loss of the label scores and to determine the semantic ranking loss according to;
J=Σ
i=1nΣ
j=1c+Σ
k=1c−
D(yc+j ,yc−k )max(0,ρ
−
xiWc+j +xiWc−k )where W is a ranking function of the neural network, n is the number of training examples, xi is an ith training example, c+ is the number of positive labels for the training example xi, c−
is the number of negative labels for the training example xi, ρ
is a margin for hinge loss, yc+j is the jth positive label, yc−k is kth negative label, D(yc+j , yc−k ) is a function that evaluates the semantic distance between two labels, yc+j and yc−k , xiWc+j is the label score given to the jth positive label when the ranking function W is used to evaluate the training example xi, and xiWc−k is the label score given to the kth negative label when the ranking function W is used to evaluate the training example xi.- View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
-
17. A system comprising:
- one or more computers and one or more storage devices storing instructions which are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;
receiving respective label scores determined by a neural network for at least two labels for at least one training example wherein at least one of the at least two labels for each training example is a positive label for the training example and at least one other of the at least two labels is a negative label for the training example; determining an error of the neural network based on a semantic ranking loss of the label scores, wherein the semantic ranking loss is determined according to; - View Dependent Claims (18, 19)
- one or more computers and one or more storage devices storing instructions which are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;
Specification