Combined scattering for rotation invariant texture analysis

By Laurent Sifre, Stéphane Mallat. 2012

68 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

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 Invariant Scattering (2011, background): “Such combined scattering representations are used for rotation invariant classification of image textures [18].”
Unsupervised Learning of Invariant Representations in Hierarchical Architectures (2013, background): “[17] implies that supp(〈TxI, t〉) ⊆ [−b + x̄, b] (see Figure 7, a)).”
Intermittent process analysis with scattering moments (2013, background): “First- and second-order scattering moments applied to image and audio textures as well as intrapartum electro-cardiograms for fetal monitoring provide state of the art classification errors [2, 9, 13, 35], but these results are strictly numerical.”
Generic Deep Networks with Wavelet Scattering (2013, methodology): “Invariant scattering transforms to translations Submitted to the workshop track of International Conference on Learning Representations (ICLR), 2014 (Bruna & Mallat, 2013) and rotation-translations (Sifre & Mallat, 2012) have previously been applied to digit recognition and texture discrimination.”
Invariant Scattering Convolution Networks (2013, background): “Building invariants to other known groups such as rotations or scaling is similarly obtained with predefined wavelets which perform convolutions along rotation or scale variables [25], [26].”
AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification (2016, methodology): “, combined scattering feature [73], was incorporated with SIFT and CH to extract structure and spectral information under a multifeature extraction”
Scattering Representations for Recognition (2013, methodology): “Building invariants to other known groups such as rotations or scaling is similarly obtained with predefined wavelets, which perform convolutions along rotation or scale variables [Mal12; SM12].”
From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, methodology): “ScatNet has been extended to achieve rotation and scale invariance [212, 213, 211] and applied to other problems besides texture such as object recognition [173].”
Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning? (2013, unknown): “(see also [50, 51] for related ideas).”
Rigid-Motion Scattering for Texture Classification (2014, background): “This is the case of separable scattering transforms (Sifre & Mallat, 2012) or any of the separable translation and rotation invariant in used in (Xu et al., 2010; Zhao et al., 2012).”
Audio Texture Synthesis with Scattering Moments (2013, background): “Scattering transforms have recently been introduced [4, 5, 6, 7] to represent audio signals and images, while providing state of the art results for texture discrimination, and genre recognition in audio [6].”