paper-with-me

Papers

Deep Haar Scattering Networks

2015-09-30 · Xiuyuan Cheng, Xu Chen, Stephane Mallat

An orthogonal Haar scattering transform is a deep network, computed with a hierarchy of additions, subtractions and absolute values, over pairs of coefficients. It provides a simple mathematical model for unsupervised deep network learning. It implements non-linear contractions, which are optimized for classification, with an unsupervised pair matching algorithm, of polynomial complexity. A structured Haar scattering over graph data computes permutation invariant representations of groups of connected points in the graph. If the graph connectivity is unknown, unsupervised Haar pair learning can provide a consistent estimation of connected dyadic groups of points. Classification results are given on image data bases, defined on regular grids or graphs, with a connectivity which may be known or unknown.

📄 PDF Abstract BibTeX arXiv:1509.09187

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral Classification

Similar Papers 제목 키워드 기반

Unsupervised Deep Haar Scattering on Graphs

2014-06-09 · NeurIPS 2014 12 · Xu Chen, Xiuyuan Cheng, Stéphane Mallat

The classification of high-dimensional data defined on graphs is particularly difficult when the graph geometry is unknown. We introduce a Haar scattering transform on graphs, which computes invariant signal descriptors.…

ClassificationDimensionality ReductionGeneral Classification

Building Function Approximators on top of Haar Scattering Networks

2018-04-09 · Fernando Fernandes Neto

In this article we propose building general-purpose function approximators on top of Haar Scattering Networks. We advocate that this architecture enables a better comprehension of feature extraction, in addition to its i…

Econometrics

Deep Haar Scattering Networks in Pattern Recognition: A promising approach

2018-11-29 · Fernando Fernandes Neto, Alemayehu Admasu Solomon, Rodrigo de Losso, Claudio Garcia 외

The aim of this paper is to discuss the use of Haar scattering networks, which is a very simple architecture that naturally supports a large number of stacked layers, yet with very few parameters, in a relatively broad s…

ClassificationGeneral ClassificationregressionTime Series+1

Near-Infrared Depth-Independent Image Dehazing using Haar Wavelets

2022-03-26 · Sumit Laha, Ankit Sharma, Shengnan Hu, Hassan Foroosh

We propose a fusion algorithm for haze removal that combines color information from an RGB image and edge information extracted from its corresponding NIR image using Haar wavelets. The proposed algorithm is based on the…

Image Dehazing

Multiscale Hodge Scattering Networks for Data Analysis

2023-11-17 · Naoki Saito, Stefan C. Schonsheck, Eugene Shvarts

We propose new scattering networks for signals measured on simplicial complexes, which we call \emph{Multiscale Hodge Scattering Networks} (MHSNs). Our construction is based on multiscale basis dictionaries on simplicial…

Descriptive