# Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks

Source: [Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks](<https://www.sota2.com/research/paper/68fa70db1e209131cea4dbba>)

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

Data updated: 2025-10-26T01:51:52.116Z

Authors: Facundo Manuel Quiroga, Franco Ronchetti, Laura Lanzarini, Aurelio Fernandez-Bariviera

Published: 2023-10-12T15:53:24.000Z

## Abstract

Convolutional Neural Networks (CNN) offer state of the art performance in various computer vision tasks. Many of those tasks require different subtypes of affine invariances (scale, rotational, translational) to image transformations. Convolutional layers are translation equivariant by design, but in their basic form lack invariances. In this work we investigate how best to include rotational invariance in a CNN for image classification. Our experiments show that networks trained with data augmentation alone can classify rotated images nearly as well as in the normal unrotated case; this increase in representational power comes only at the cost of training time. We also compare data augmentation versus two modified CNN models for achieving rotational invariance or equivariance, Spatial Transformer Networks and Group Equivariant CNNs, finding no significant accuracy increase with these specialized methods. In the case of data augmented networks, we also analyze which layers help the network to encode the rotational invariance, which is important for understanding its limitations and how to best retrain a network with data augmentation to achieve invariance to rotation.

## 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/2310.08429>)

[PDF](<https://arxiv.org/pdf/2310.08429.pdf>)
