Results 51 to 60 of about 116,308 (181)

Zero Shot Learning with the Isoperimetric Loss

, 2019
We introduce the isoperimetric loss as a regularization criterion for learning the map from a visual representation to a semantic embedding, to be used to transfer knowledge to unknown classes in a zero-shot learning setting.
Bertozzi, Andrea, Deutsch, Shay, Soatto, Stefano   +2 more
core   +1 more source

Structure-Aware Classification using Supervised Dictionary Learning

, 2016
In this paper, we propose a supervised dictionary learning algorithm that aims to preserve the local geometry in both dimensions of the data. A graph-based regularization explicitly takes into account the local manifold structure of the data points.
Elad, Michael, Yankelevsky, Yael
core   +1 more source

Optimal regular graph designs [PDF]

Statistics and Computing, 2017
A typical problem in optimal design theory is finding an experimental design that is optimal with respect to some criteria in a class of designs. The most popular criteria include the A- and D-criteria. Regular graph designs occur in many optimality results and, if the number of blocks is large enough, they are A- and D-optimal.
openaire   +3 more sources

Hyperspectral Anomaly Detection via Low-Rank Representation with Dual Graph Regularizations and Adaptive Dictionary

Remote Sensing
In a hyperspectral image, there is a close correlation between spectra and a certain degree of correlation in the pixel space. However, most existing low-rank representation (LRR) methods struggle to utilize these two characteristics simultaneously to ...
Xi Cheng, Ruiqi Mu, Sheng Lin, Min Zhang, Hai Wang   +4 more
doaj   +1 more source

Nonlinear and oblique boundary value problems for the Stokes equations

Electronic Journal of Qualitative Theory of Differential Equations, 2011
In this paper we consider the nonlinear boundary value problem governed by a stationary perturbed Stokes system with mixed boundary conditions (Dirichlet- maximal monotone graph), in a smooth domain.
Hamid Benseridi, Mourad Dilmi
doaj   +1 more source

Semantic Consistency Cross-Modal Retrieval With Semi-Supervised Graph Regularization

IEEE Access, 2020
Most of the existing cross-modal retrieval methods make use of labeled data to learn projection matrices for different modal data. These methods usually learn the original semantic space to bridge the heterogeneous gap, ignoring the rich semantic ...
Gongwen Xu, Xiaomei Li, Zhijun Zhang
doaj   +1 more source

Motivic renormalization and singularities [PDF]

, 2009
We consider parametric Feynman integrals and their dimensional regularization from the point of view of differential forms on hypersurface complements and the approach to mixed Hodge structures via oscillatory integrals.
Marcolli, Matilde
core   +2 more sources

Iterative graph cuts for image segmentation with a nonlinear statistical shape prior

, 2013
Shape-based regularization has proven to be a useful method for delineating objects within noisy images where one has prior knowledge of the shape of the targeted object.
A. O’Hagan, B. Silverman, D. Cremers, D. Cremers, D. Cremers, D. Cremers, D. Freedman, D. Freedman, D. Hunter, G. Slabaugh, J. Chang, J. Malcolm, J. Malcolm, J. Schindelin, J. Zhu-Jacquot, Joshua C. Chang, L. Grady, N. El Zehiry, N. Vu, O. Veksler, P. Das, P. Kohli, P. Viola, S. Belongie, S. Dambreville, S. Lee, S. Tabbone, S.C. Pei, T. Heimann, T. Jiang, Tom Chou, V. Lempitsky, V. Lempitsky, V. Vineet, Y. Boykov, Y. Boykov, Y. Boykov   +36 more
core   +1 more source

Accounting for apparatus function when registering experimental data: peculiarity of choosing regularization parameter by L-curve criterion at deconvolution of the spectrum

Ядерна фізика та енергетика, 2019
Within the framework of the problem of spectrum deconvolution, variant of the choice of the regularization parameter by criterion of the L-curve, based on the displacement along the points of the L-curve graph, is proposed. An analysis of dependencies on
A. M. Sokolov
doaj   +1 more source

Cross-media retrieval method fusing with coupled dictionary learning and image regularization [PDF]

Jisuanji gongcheng, 2019
The method of cross-media retrieval mostly maps the original features of two modalities to the common subspace,and performs cross-media retrieval in the subspace,ignoring the selection of discriminant features and the relationship between modalities ...
LIU Yun,YU Zhilou,FU Qiang
doaj   +1 more source