cs.CVNov 6, 2026

Graded convolutional networks: scale invariance without the scale and robustness to unknown blur

Authors: Tanush Shaska

Abstract

The Gaussian jet of an image is a graded vector space: a dilation by λλ multiplies derivatives of order kk by λ−kλ^{-k}. Local graded convolutions are exactly homogeneous differential operators, and a local feature is dilation-invariant if and only if it factors through the scale-normalized jet or, without the scale, through the retraction onto the weighted sphere of the grading. Under unknown Gaussian blur the retraction changes only by a change of scale, whereas the scale-normalized jet acquires a grading factor that no radial normalization removes. At the zero jet the retraction separates image families that radial normalizations and continuous classifiers cannot. Networks built on the retraction are universal for invariant features. On MNIST such a network keeps 88.4% accuracy under a two-pixel blur, against 66.2% for the same network on scale-normalized derivatives; in Lindeberg's Gaussian derivative network the retraction raises accuracy at that blur from 91.5% to 95.1%.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Scale-invariant Gaussian derivative residual networks

    Mar 3, 2026Andrzej Perzanowski, Tony LindebergOOD GeneralizationEquivariant Neural Networks

  2. Neural Disjunctive Normal Forms for Learning Exact Rank Filters

    Oct 23, 2026Diego Marcondes, Wonder A. L. Alves, Ronaldo F. Hashimoto