# Rotated Ring, Radial and Depth Wise Separable Radial Convolutions

arXiv: https://arxiv.org/abs/2010.00873 · HTML: https://mlsanity.com/paper/2010.00873/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2020.

## Built on by (most cited first, 12 of 12)

- [TEyeD: Over 20 million real-world eye images with Pupil, Eyelid, and Iris 2D and 3D Segmentations, 2D and 3D Landmarks, 3D Eyeball, Gaze Vector, and Eye Movement Types](https://mlsanity.com/paper/2102.02115/) (2021)
- [The Gaze and Mouse Signal as additional Source for User Fingerprints in Browser Applications](https://mlsanity.com/paper/2101.03793/) (2021)
- [A Multimodal Eye Movement Dataset and a Multimodal Eye Movement Segmentation Analysis](https://mlsanity.com/paper/2101.04318/) (2021)
- [1000 Pupil Segmentations in a Second using Haar Like Features and Statistical Learning](https://mlsanity.com/paper/2102.01921/) (2021)
- [Maximum and Leaky Maximum Propagation](https://mlsanity.com/paper/2105.10277/) (2021)
- [Tensor Normalization and Full Distribution Training](https://mlsanity.com/paper/2109.02345/) (2021)
- [GroupGazer: A Tool to Compute the Gaze per Participant in Groups with integrated Calibration to Map the Gaze Online to a Screen or Beamer Projection](https://mlsanity.com/paper/2201.07692/) (2022)
- [SRE-Conv: Symmetric Rotation Equivariant Convolution for Biomedical Image Classification](https://mlsanity.com/paper/2501.09753/) (2025)
- [Improved Vessel Segmentation with Symmetric Rotation-Equivariant U-Net](https://mlsanity.com/paper/2501.14592/) (2025)
- [GMR-Conv: An Efficient Rotation and Reflection Equivariant Convolution Kernel Using Gaussian Mixture Rings](https://mlsanity.com/paper/2504.02819/) (2025)
- [Technical Report: Combining knowledge from Transfer Learning during training and Wide Resnets](https://mlsanity.com/paper/2206.09697/) (2022)
- [Equivariant Imaging Biomarkers for Robust Unsupervised Segmentation of Histopathology](https://mlsanity.com/paper/2505.05689/) (2025)

## Abstract (arXiv)

Simple image rotations significantly reduce the accuracy of deep neural networks. Moreover, training with all possible rotations increases the data set, which also increases the training duration. In this work, we address trainable rotation invariant convolutions as well as the construction of nets, since fully connected layers can only be rotation invariant with a one-dimensional input. On the one hand, we show that our approach is rotationally invariant for different models and on different public data sets. We also discuss the influence of purely rotational invariant features on accuracy. The rotationally adaptive convolution models presented in this work are more computationally intensive than normal convolution models. Therefore, we also present a depth wise separable approach with radial convolution. Link to CUDA code https://atreus.informatik.uni-tuebingen.de/seafile/d/8e2ab8c3fdd444e1a135/