Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination

By Laurent Sifre, Stéphane Mallat. 2013

468 citations recorded by the source corpus.

An affine invariant representation is constructed with a cascade of invariants, which preserves information for classification. A joint translation and rotation invariant representation of image patches is calculated with a scattering transform. It is implemented with a deep convolution network, which computes successive wavelet transforms and modulus non-linearities. Invariants to scaling, shearing and small deformations are calculated with linear operators in the scattering domain. State-of-the-art classification results are obtained over texture databases with uncontrolled viewing conditions.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Xception: Deep Learning with Depthwise Separable Convolutions (2016, positive): “This initial work on depthwise separable convolutions was inspired by prior research from Sifre and Mallat on transformation-invariant scattering [16, 15].”
Making Convolutional Networks Shift-Invariant Again (2019, background): “Recent work has strived to build in additional types of in-variances, such as rotation, reﬂection, and scaling (Sifre & Mallat, 2013; Bruna & Mallat, 2013; Esteves et al., 2018; Kanazawa et al., 2014; Worrall et al., 2017; Cohen & Welling, 2016).”
Describing Textures in the Wild (2013, methodology): “We also experimented with the state-of-the-art descriptor of [32] which we did not ﬁnd to be competitive with IFV on FMD and DTD (Tab.”
Scattering Networks for Hybrid Representation Learning (2018, methodology): “It is even possible to build a scattering transform on the roto-translation group [48].”
One Model To Learn Them All (2017, methodology): “Depthwise separable convolutions were ﬁrst studied by Sifre [26] and later they were used to get good results on large-scale image classiﬁcation with Xception [5].”
Why do deep convolutional networks generalize so poorly to small image transformations? (2018, methodology): “Alternatively, one could use specially designed features such as SIFT in which invariance is hard coded [7, 29, 30, 31] or neural network architectures that explicitly enforce invariance [36, 19, 5, 6, 11, 12, 47, 46, 8].”
General E(2)-Equivariant Steerable CNNs (2019, background): “…a wide range of equivariant models, covering regular GCNNs [6, 7, 8, 9, 10, 11], classical Steerable CNNs [1], Harmonic Networks [12], gated Harmonic Networks [2], Vector Field Networks [13], Scattering Transforms [14, 15, 16, 17, 18] and entirely new architectures, in one uniﬁed framework.”
Group Equivariant Convolutional Networks (2016, methodology): “Scattering networks have been extended to use convolutions on the group of translations, rotations and scalings, and have been applied to object and texture recognition (Sifre & Mallat, 2013; Oyallon & Mallat, 2015).”
RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks (2018, background): “The joint convolution across space and rotation has been studied in the scattering transform [25, 33].”
Understanding Image Representations by Measuring Their Equivariance and Equivalence (2014, neutral): “This is even more explicit in the scattering transform of Sifre and Mallat [22].”
Understanding deep convolutional networks (2016, methodology): “It is used by joint scattering transforms [21,27] and has been proposed for unsupervised convolution network learning [28].”
Depthwise Separable Convolutions for Neural Machine Translation (2017, background): “Depthwise separable convolutions were first studied by Sifre [18] during a 2013 internship at Google Brain, and were first introduced in an ICLR 2014 presentation [22].”
Scaling the Scattering Transform: Deep Hybrid Networks (2017, positive): “A major improvement over SIFT can be found in the scattering transform [24, 6, 33], which is a type of deep convolutional network, which permits to retain discriminative information normally discarded by methods like SIFT while introducing geometric invariances and stability.”
Rotation Equivariant Vector Field Networks (2016, methodology): “[23] use hand crafted wavelets that are separable in the roto-translational space, allowing for more efficient computations.”
A General Theory of Equivariant CNNs on Homogeneous Spaces (2018, neutral): “Other related work includes [24–31].”