S2P-Net: A Spectral-Spatial Polar Network for Rotation-Invariant Object Recognition in Low-Data Regimes

TL;DR

S2P-Net is a compact deep learning model designed to achieve rotation invariance mathematically without data augmentation, outperforming other architectures in low-data regimes.

Contribution

The paper introduces S2P-Net, a novel spectral-spatial polar network that guarantees rotation invariance inherently, reducing reliance on data augmentation.

Findings

S2P-Net achieves rotation invariance mathematically.

It performs well in low-data regimes.

Comparison shows advantages over CNN architectures.

Abstract

We present S2P-Net (Spectral-Spatial Polar Network), a compact deep learning architecture that achieves mathematically guaranteed rotation invariance without data augmentation. In this Paper, we also made a comparison to other neural network architectures (CNN`s). Have a look at the results and feel free to contact me for any questions. This is my first paper:) Made by Hackbert