TY - GEN
T1 - Learning local invariant mahalanobis distances
AU - Fetaya, Ethan
AU - Ullman, Shimon
PY - 2015
Y1 - 2015
N2 - For many tasks and data types, there are natural transformations to which the data should be invariant or insensitive. For instance, in visual recognition, natural images should be insensitive to rotation and translation. This requirement and its implications have been important in many machine learning applications, and tolerance for image transformations was primarily achieved by using robust feature vectors. In this paper we propose a novel and computationally efficient way to learn a local Mahalanobis metric per datum, and show how we can learn a local invariant metric to any transformation in order to improve performance.
AB - For many tasks and data types, there are natural transformations to which the data should be invariant or insensitive. For instance, in visual recognition, natural images should be insensitive to rotation and translation. This requirement and its implications have been important in many machine learning applications, and tolerance for image transformations was primarily achieved by using robust feature vectors. In this paper we propose a novel and computationally efficient way to learn a local Mahalanobis metric per datum, and show how we can learn a local invariant metric to any transformation in order to improve performance.
UR - http://www.scopus.com/inward/record.url?scp=84969584364&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:84969584364
T3 - 32nd International Conference on Machine Learning, ICML 2015
SP - 162
EP - 168
BT - 32nd International Conference on Machine Learning, ICML 2015
A2 - Bach, Francis
A2 - Blei, David
PB - International Machine Learning Society (IMLS)
T2 - 32nd International Conference on Machine Learning, ICML 2015
Y2 - 6 July 2015 through 11 July 2015
ER -