Target domain characterization for data augmentation
First Claim
Patent Images
1. A method for training data augmentation, said method comprising:
- providing a source domain and a target domain;
augmenting data in said source domain with transformations utilizing characteristics learned from said target domain wherein said characteristics include unlabeled images from said target domain;
employing augmented data from said source domain to said transformations to improve image classification accuracy in said target domain or a new domain; and
determining at least one representative property of said target domain and said source domain utilizing an average of one property from a set of images and wherein said photometric transformation comprises an intensity clipping.
6 Assignments
0 Petitions
Accused Products
Abstract
Methods, systems, and processor-readable media for training data augmentation. A source domain and a target domain are provided, and thereafter an operation is performed to augment data in the source domain with transformations utilizing characteristics learned from the target domain. The augmented data is then used to improve image classification accuracy in a new domain.
41 Citations
18 Claims
-
1. A method for training data augmentation, said method comprising:
-
providing a source domain and a target domain; augmenting data in said source domain with transformations utilizing characteristics learned from said target domain wherein said characteristics include unlabeled images from said target domain; employing augmented data from said source domain to said transformations to improve image classification accuracy in said target domain or a new domain; and determining at least one representative property of said target domain and said source domain utilizing an average of one property from a set of images and wherein said photometric transformation comprises an intensity clipping. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A system for training data augmentation, said system comprising:
-
at least one processor; and a non-transitory computer-usable medium embodying computer program code, said computer-usable medium capable of communicating with said at least one processor, said computer program code comprising instructions executable by said at least one processor and configured for; providing a source domain and a target domain; augmenting data in said source domain with transformations utilizing characteristics learned from said target domain, wherein said characteristics include unlabeled images from said target domain; employing augmented data from said source domain said transformations to improve image classification accuracy in said target domain or a new domain; and determining at least one representative property of said target domain and said source domain utilizing an average of one property from a set of images and wherein said photometric transformation comprises an intensity clipping. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17)
-
-
18. A system for training data augmentation, said system comprising:
-
at least one processor; and a non-transitory computer-usable medium embodying computer program code, said computer-usable medium capable of communicating with said at least one processor, said computer program code comprising instructions executable by said at least one processor and configured for; providing a source domain and a target domain; augmenting data in said source domain with transformations utilizing characteristics learned from said target domain, wherein said characteristics include unlabeled images from said target domain; employing augmented data from said source domain said transformations to improve image classification accuracy in a new domain; determining at least one representative property of said target domain and said source domain utilizing an average of one property from a set of images and wherein said photometric transformation comprises an intensity clipping; training a model for said source domain with said augmented data; fine-tuning said model to derive a refined model for said target domain; and deriving a new model for said target domain after training said model for said source domain with said augmented data wherein a SVM (Support Vector Machine) is supplied to said new model for said target domain.
-
Specification