# Rotation invariant CNN using scattering transform for image classification

Source: [Rotation invariant CNN using scattering transform for image classification](<https://www.sota2.com/research/paper/68fa6a061e209131cea25884>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:14:37.392Z

Authors: Rosemberg Rodriguez Salas, Eva Dokladalova, Petr Dokl\\'adal

Published: 2021-05-21T07:36:34.000Z

## Abstract

Deep convolutional neural networks accuracy is heavily impacted by rotations of the input data. In this paper, we propose a convolutional predictor that is invariant to rotations in the input. This architecture is capable of predicting the angular orientation without angle-annotated data. Furthermore, the predictor maps continuously the random rotation of the input to a circular space of the prediction. For this purpose, we use the roto-translation properties existing in the Scattering Transform Networks with a series of 3D Convolutions. We validate the results by training with upright and randomly rotated samples. This allows further applications of this work on fields like automatic re-orientation of randomly oriented datasets.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2105.10175>)

[PDF](<https://arxiv.org/pdf/2105.10175.pdf>)