High-order Tensor Regularization with Application to Attribute Ranking

Kim, Kwang In and Park, Juhyun and Tompkin, James (2018) High-order Tensor Regularization with Application to Attribute Ranking. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition :. IEEE, pp. 4349-4357. ISBN 9781538664209

[thumbnail of Kim_High-Order_Tensor_Regularization_CVPR_2018_paper]
PDF (Kim_High-Order_Tensor_Regularization_CVPR_2018_paper)
Kim_High_Order_Tensor_Regularization_CVPR_2018_paper.pdf - Accepted Version
Available under License Unspecified.

Download (950kB)


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.

Item Type:
Contribution in Book/Report/Proceedings
Additional Information:
©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.
ID Code:
Deposited By:
Deposited On:
13 Mar 2019 14:55
Last Modified:
31 Dec 2023 01:37