Scattering Networks for Hybrid Representation Learning

By Edouard Oyallon, Sergey Zagoruyko, Gabriel Huang, Nikos Komodakis, Simon Lacoste-Julien, Matthew B. Blaschko, Eugene Belilovsky. 2018

99 citations recorded by the source corpus.

Scattering networks are a class of designed Convolutional Neural Networks (CNNs) with fixed weights. We argue they can serve as generic representations for modelling images. In particular, by working in scattering space, we achieve competitive results both for supervised and unsupervised learning tasks, while making progress towards constructing more interpretable CNNs. For supervised learning, we demonstrate that the early layers of CNNs do not necessarily need to be learned, and can be replaced with a scattering network instead. Indeed, using hybrid architectures, we achieve the best results with predefined representations to-date, while being competitive with end-to-end learned CNNs. Specifically, even applying a shallow cascade of small-windowed scattering coefficients followed by $1\times 1$1×1-convolutions results in AlexNet accuracy on the ILSVRC2012 classification task. Moreover, by combining scattering networks with deep residual networks, we achieve a single-crop top-5 error of 11.4 percent on ILSVRC2012. Also, we show they can yield excellent performance in the small sample regime on CIFAR-10 and STL-10 datasets, exceeding their end-to-end counterparts, through their ability to incorporate geometrical priors. For unsupervised learning, scattering coefficients can be a competitive representation that permits image recovery. We use this fact to train hybrid GANs to generate images. Finally, we empirically analyze several properties related to stability and reconstruction of images from scattering coefficients.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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 Representation & Self-Supervised Learning

Citations in the corpus

Differentially Private Learning Needs Better Features (or Much More Data) (2020, positive): “Notably, Oyallon et al. (2018) match the (non-private) accuracy of AlexNet (Krizhevsky et al., 2012) on ImageNet with a small six-layer CNN trained on ScatterNet features.”
Kymatio: Scattering Transforms in Python (2018, methodology): “It is also eﬀective in combination with modern representation learning approaches (Oyallon et al., 2018; Sainath et al., 2014; Zeghidour et al., 2016).”
On Translation Invariance in CNNs: Convolutional Layers Can Exploit Absolute Spatial Location (2020, background): “The seminial Scattering network [10] and its variants [74, 75] design a convolutional architecture to incorporate physical priors about image deformations.”