REVIEW 6 cited by
Invariant Scattering Convolution Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Invariant Scattering Convolution Networks
read the original abstract
A wavelet scattering network computes a translation invariant image representation, which is stable to deformations and preserves high frequency information for classification. It cascades wavelet transform convolutions with non-linear modulus and averaging operators. The first network layer outputs SIFT-type descriptors whereas the next layers provide complementary invariant information which improves classification. The mathematical analysis of wavelet scattering networks explains important properties of deep convolution networks for classification. A scattering representation of stationary processes incorporates higher order moments and can thus discriminate textures having the same Fourier power spectrum. State of the art classification results are obtained for handwritten digits and texture discrimination, using a Gaussian kernel SVM and a generative PCA classifier.
Forward citations
Cited by 6 Pith papers
-
Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection
Retrieval from out-of-domain foundation models enables personalization of a lightweight transformer for stress detection, yielding +3.92% accuracy and +4.76% F1 gains on WESAD without user labels.
-
Small-scale Lyman alpha forest cosmology with PRIYA: Constraints from XQ100 and KODIAQ-SQUAD one-dimensional flux power spectra
The XQ100 Lyman-alpha forest power spectrum, modeled with the PRIYA simulations, gives cosmological constraints consistent with eBOSS and Planck and constrains the IGM thermal history without external temperature data...
-
Multi-branch classification of diffuse cluster radio emission
DualSSN (scattering + SE dual-branch) with beam-normalised cropping and mild uv-tapering reaches ~0.86 accuracy (top-5 ensemble 0.94) on LoTSS-DR2/PSZ2 diffuse-emission labels, beating simple CNNs and fixed FoV/pixel crops.
-
Inferring Cosmology and Astrophysics from the High-redshift 21cm Signal with SKA-Low
A review chapter on tools for inferring galaxy and IGM properties from the 21 cm signal using the initial SKA-Low array configuration.
-
Overview of 21cm Experiments at high redshift with SKAO
Overview of SKA-Low 21cm experiments for high-redshift cosmology, covering power spectra, tomography, 21cm forest, cross-correlations, and key telescope features.
-
Overview of 21cm Experiments at high redshift with SKAO
An overview summarizing SKA-Low 21cm experiments for power spectrum, tomography, 21-cm forest, and cross-correlations, plus critical telescope features, building on the 2015 SKA Science Book.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.