Accepted author manuscript, 929 KB, PDF document
Available under license: Unspecified
Final published version
Final published version
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - High-order Tensor Regularization with Application to Attribute Ranking
AU - Kim, Kwang In
AU - Park, Juhyun
AU - Tompkin, James
N1 - ©2018 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
PY - 2018/6/18
Y1 - 2018/6/18
N2 - When learning functions on manifolds, we can improve performance by regularizing with respect to the intrinsic manifold geometry rather than the ambient space. However, when regularizing tensor learning, calculating the derivatives along this intrinsic geometry is not possible, and so existing approaches are limited to regularizing in Euclidean space. Our new method for intrinsically regularizing and learning tensors on Riemannian manifolds introduces a surrogate object to encapsulate the geometric characteristic of the tensor. Regularizing this instead allows us to learn non-symmetric and high-order tensors. We apply our approach to the relative attributes problem, and we demonstrate that explicitly regularizing high-order relationships between pairs of data points improves performance.
AB - When learning functions on manifolds, we can improve performance by regularizing with respect to the intrinsic manifold geometry rather than the ambient space. However, when regularizing tensor learning, calculating the derivatives along this intrinsic geometry is not possible, and so existing approaches are limited to regularizing in Euclidean space. Our new method for intrinsically regularizing and learning tensors on Riemannian manifolds introduces a surrogate object to encapsulate the geometric characteristic of the tensor. Regularizing this instead allows us to learn non-symmetric and high-order tensors. We apply our approach to the relative attributes problem, and we demonstrate that explicitly regularizing high-order relationships between pairs of data points improves performance.
U2 - 10.1109/CVPR.2018.00457
DO - 10.1109/CVPR.2018.00457
M3 - Conference contribution/Paper
SP - 4349
EP - 4357
BT - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
PB - IEEE
T2 - EventIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018
Y2 - 18 June 2018 through 22 June 2018
ER -