jangwon-kim-cocel/Radon-Averaging

Radon Averaging

A Practical Approach for Designing Rotation-Invariant Models

        

---

Engineering Applications of Artificial Intelligence (EAAI 2026)

Pytorch Implementation

This repository contains a pytorch implementation of Radon Averaging (RA) of the paper:

Radon Averaging: A practical approach for designing rotation-invariant models
Jangwon Kim, Sanghyun Ryoo, Jiwon Kim, Junkee Hong, Soohee Han
Engineering Applications of Artificial Intelligence, Volume 164, 2026

📄 Paper Link

DOI: https://doi.org/10.1016/j.engappai.2025.113299
Journal: Engineering Applications of Artificial Intelligence

---

Radon Averaging

Radon Averaging achieves rotation invariance by: 1. Radon Transform (ℛ): Converts images ($I$) to sinograms, where an rotation corresponds ($$g$$) to a circular shift. 2. Averaging over Discrete Rotations ($$G$$): Eliminates boundary artifacts via group averaging 3. Standard CNN Backbone ($$Φ$$): No architectural changes required
$$R{A}_G^{\mathrm{\Phi }}(I)=\frac{1}{\mathrm{\mid }G\mathrm{\mid }}\sum _{g\in G}(\mathrm{\Phi }\circ \pi (g)\circ \mathcal{R})(I)RA\_G^\Phi (I)\; =\; \backslash frac\{1\}\{|G|\}\; \backslash sum\_\{g\; \backslash in\; G\}\; (\Phi \; \backslash circ\; \pi (g)\; \backslash circ\; ℛ)(I)$$

Advantages

• Plug-and-play: works with standard (pretrained) CNN backbones (no architectural changes).
• Rotation invariance in practice: stable representations under image rotations.
• Reduces boundary artifacts: group averaging mitigates Radon transform edge effects.

---

Citation Example

@article{kim2026radonaveraging,
  title   = {Radon Averaging: A practical approach for designing rotation-invariant models},
  author  = {Kim, Jangwon and Ryoo, Sanghyun and Kim, Jiwon and Hong, Junkee and Han, Soohee},
  journal = {Engineering Applications of Artificial Intelligence},
  volume  = {164},
  pages   = {113299},
  year    = {2026},
  doi     = {10.1016/j.engappai.2025.113299}
}