Deep Haar Scattering Networks
By Xiuyuan Cheng, Xu Chen, Stéphane Mallat. 2015
31 citations recorded by the source corpus.
An orthogonal Haar scattering transform is a deep network computed with a hierarchy of additions, subtractions and absolute values over pairs of coefficients. Unsupervised learning optimizes Haar pairs to obtain sparse representations of training data with an algorithm of polynomial complexity. For signals defined on a graph, a Haar scattering is computed by cascading orthogonal Haar wavelet transforms on the graph, with Haar wavelets having connected supports. It defines a representation which is invariant to local displacements of signal values on the graph. When the graph connectivity is unknown, unsupervised Haar learning can provide a consistent estimation of connected wavelet supports. Classification results are given on image data bases, defined on regular grids or graphs, with a connectivity which may be known or unknown.
Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning, Model Architectures
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Aerospace Engineering
- Yoshua Bengio
- Joan Bruna
- Pascal Vincent
- Arthur Szlam
- Yann LeCun
- Pierre Vandergheynst
- Michael M. Bronstein
- Vincent Lepetit
In Computer Vision and Pattern Recognition
- Yoshua Bengio
- Luc Van Gool
- Dacheng Tao
- Xiaogang Wang
- Trevor Darrell
- Jitendra Malik
- Ming-Hsuan Yang
- Andrea Vedaldi
In Representation & Self-Supervised Learning
- Yoshua Bengio
- Pascal Vincent
- Yann LeCun
- Guillaume Alain
- Joan Bruna
- Jason Yosinski
- Kyunghyun Cho
- L. Yao
In Model Architectures
- Yoshua Bengio
- Michael M. Bronstein
- Joan Bruna
- Yann LeCun
- Arthur Szlam
- Pascal Vincent
- Saizheng Zhang
- L. Yao
Citations in the corpus
- GSNs : Generative Stochastic Networks (2015, background): “See also the work on learning invariant representations in this issue (Anselmi et al., 2016; Cheng et al., 2016).”
- Geometric Deep Learning: Going beyond Euclidean data (2016, methodology): “In [88], ensembles of Haar wavelet decompositions were used to define deep wavelet scattering transforms on general domains, obtaining excellent numerical performance.”