Multiscale Hierarchical Convolutional Networks

By Jörn-Henrik Jacobsen, Edouard Oyallon, Stéphane Mallat, Arnold M. W. Smeulders. 2017

17 citations recorded by the source corpus.

Deep neural network algorithms are difficult to analyze because they lack structure allowing to understand the properties of underlying transforms and invariants. Multiscale hierarchical convolutional networks are structured deep convolutional networks where layers are indexed by progressively higher dimensional attributes, which are learned from training data. Each new layer is computed with multidimensional convolutions along spatial and attribute variables. We introduce an efficient implementation of such networks where the dimensionality is progressively reduced by averaging intermediate layers along attribute indices. Hierarchical networks are tested on CIFAR image data bases where they obtain comparable precisions to state of the art networks, with much fewer parameters. We study some properties of the attributes learned from these databases.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

In Model Architectures

Citations in the corpus

Scattering Networks for Hybrid Representation Learning (2018, background): “Finding structure in the kernel of the layers of depth less than 2 [56], [60] is a complex task, and few empirical analyses exist that shed light on the structure [28] of deeper layers.”
Scaling the Scattering Transform: Deep Hybrid Networks (2017, neutral): “Recent works [25, 7, 17] have suggested that deep networks could build an approximation of the group of symmetries of a classification task and apply transformations along the orbits of this group, like convolutions.”
Multi-Scale Dense Networks for Resource Efficient Image Classification (2017, background): “Our network architecture borrows elements from neural fabrics (Saxena & Verbeek, 2016) and others (Jacobsen et al., 2017; Ke et al., 2016) to rapidly construct a low-resolution feature map that is amenable to classification, whilst also maintaining feature maps of higher resolution that are essentia”