Devices, systems, and methods for learning a discriminant image representation
First Claim
1. A method comprising:
- obtaining a set of low-level features from each image in a set of images, wherein each image is associated with one or more labels in a set of labels;
generating a respective high-dimensional generative representation of each image based on the low-level features;
generating a respective lower-dimensional representation of each image based on the respective high-dimensional generative representation of the image;
generating respective classifiers for each label in the set of labels based on one or more of the high-dimensional generative representations of the images that are associate with the label and the lower-dimensional representations of the images that are associated with the label; and
generating a respective combined representation for each image, wherein the combined representation includes the respective classifiers of the labels that are associated with the respective image and includes the lower-dimensional representation of the respective image, and wherein the respective combined representation for an image is generated according to
{tilde over (x)}ij=λ
·
wi+(1−
λ
)·
xij,where xij denotes the lower-dimensional representation of the image, where {tilde over (x)}ij denotes the respective combined representation of the image, where wi denotes the respective classifiers of the labels that are associated with the image, and where λ
is a regularization parameter.
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.
-
Citations
16 Claims
-
1. A method comprising:
-
obtaining a set of low-level features from each image in a set of images, wherein each image is associated with one or more labels in a set of labels; generating a respective high-dimensional generative representation of each image based on the low-level features; generating a respective lower-dimensional representation of each image based on the respective high-dimensional generative representation of the image; generating respective classifiers for each label in the set of labels based on one or more of the high-dimensional generative representations of the images that are associate with the label and the lower-dimensional representations of the images that are associated with the label; and generating a respective combined representation for each image, wherein the combined representation includes the respective classifiers of the labels that are associated with the respective image and includes the lower-dimensional representation of the respective image, and wherein the respective combined representation for an image is generated according to
{tilde over (x)}ij=λ
·
wi+(1−
λ
)·
xij,where xij denotes the lower-dimensional representation of the image, where {tilde over (x)}ij denotes the respective combined representation of the image, where wi denotes the respective classifiers of the labels that are associated with the image, and where λ
is a regularization parameter.- View Dependent Claims (2, 3, 4)
-
-
5. A method comprising:
-
obtaining a query image; generating a high-dimensional generative representation of low-level features the query image; generating a lower-dimensional representation of the low-level features of the query image based on the high-dimensional generative representation; and generating a comparison score for the query image and a reference image based on the lower-dimensional representation of the query image and on a combined representation of the reference image, wherein the combined representation of the reference image includes one or more classifiers and a lower-dimensional representation of the reference image, and wherein the combined representation of the reference image was generated according to
{tilde over (x)}ij=λ
·
wi+(1−
λ
)·
xij,where xij is the lower-dimensional representation of the reference image, where wi is a respective classifier of a label that is associated with the reference image, and where λ
is a weighting parameter.- View Dependent Claims (6, 7, 8, 9, 10, 11, 15, 16)
where x is the lower-dimensional representation of the query image, where κ
on(x,xij) is the comparison score, where s(x,xij) is a matching score between the lower-dimensional representation of the query image x and the lower-dimensional representation of the reference image xij, where li(x) is a classifier output, and where λ
is a weighting parameter.
-
-
8. The method of claim 7, wherein the matching score is a cosine distance, where s(x,xij)=xijTx, and where the lower-dimensional representation of the the query image x and the lower-demensional representation of the reference image xij have been pre-normalized by L2-normalization.
-
9. The method of claim 5, wherein the comparison score is generated by a dot-product operation.
-
10. The method of claim 5, wherein the comparison score is further based on a significance of the reference image, and wherein the significance of the reference image is a classification confidence g(xij) that can be computed according to
-
11. The method of claim 10, wherein the comparison score κ
- (x,xij) can be described according to
κ
(x,xij)=λ
·
κ
on(x,xij)+(1−
λ
)·
g(xij),where κ
on(x,xij) is a function that compares the lower-dimensional reprentation of the query image to the combined representation of the reference image, where g(xij) is the classification confidence, and where γ
is a weighting parameter.
- (x,xij) can be described according to
-
15. The method of claim 6, wherein the category vector is a category mean vector of an LDA classifier or is a normal vector of an SVM classifier.
-
16. The method of claim 9, wherein the comparison score is generated according to
κ-
on(x,xij)={tilde over (x)}ijTx,
where {tilde over (x)}ij is the combined representation of the reference image and where x is the query image.
-
on(x,xij)={tilde over (x)}ijTx,
-
12. One or more computer-readable storage media storing instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations comprising:
-
obtaining low-level features from each image in a set of images, wherein each image is associated with one or more labels in a set of labels; generating a high-dimensional representation for each image based on the low-level features of the respective image; generating a lower-dimensional representation for each image based on the high-dimensional representation of the respective image; generating a classifier for each label in the set of labels based on the high-dimensional representations of the respective images that are associated with the label or the lower-dimensional representations of the respective images that are associated with the label; and generating a respective combined representation for each image, wherein the respective combined representation of an image includes the respective classifiers of the one or more labels that are associated with the respective image and includes the lower-dimensional representation of the respective image, and wherein the respective combined representation for an image is generated according to
{tilde over (x)}ij=λ
·
wi+(1−
λ
)·
xij,where xij denotes the lower-dimensional representation of the image, where {tilde over (x)}ij denotes the respective combined representation of the image, where wi denotes the respective classifiers of the labels that are associated with the image and where λ
is a regularization parameter. - View Dependent Claims (13, 14)
-
Specification