8 citations · 11 across the 3 of their papers we have counts for
7 papers
Understanding the Effects of Projectors in Knowledge Distillation
Yudong Chen, Sen Wang, Jiajun Liu +4
Conventionally, during the knowledge distillation process (e.g. feature distillation), an additional projector is often required to perform feature transformation due to the dimens…
A Note on Error Bounds for Pseudo Skeleton Approximations of Matrices
Frank de Hoog, Markus Hegland
Due to their importance in both data analysis and numerical algorithms, low rank approximations have recently been widely studied. They enable the handling of very large matrices.…
On the van Cittert - Zernike theorem for intensity correlations and its applications
Timur E. Gureyev, Alexander Kozlov, David M. Paganin +3
A reciprocal relationship between the autocovariance of the light intensity in the source plane and in the far-field detector plane is presented in a form analogous to the classica…
Compressive hyperspectral imaging via adaptive sampling and dictionary learning
Mingrui Yang, Frank de Hoog, Yuqi Fan +1
In this paper, we propose a new sampling strategy for hyperspectral signals that is based on dictionary learning and singular value decomposition (SVD). Specifically, we first lear…
Hyperspectral Image Recovery via Hybrid Regularization
Reza Arablouei, Frank de Hoog
Natural images tend to mostly consist of smooth regions with individual pixels having highly correlated spectra. This information can be exploited to recover hyperspectral images o…
On spatial resolution, signal-to-noise and information capacity of linear imaging systems
Timur Gureyev, Yakov Nesterets, Frank de Hoog
A simple model for image formation in linear shift-invariant systems is considered, in which both the detected signal and the noise variance are varying slowly compared to the poin…