# TorMentor: Deterministic dynamic-path, data augmentations with fractals

arXiv: https://arxiv.org/abs/2204.03776 · HTML: https://mlsanity.com/paper/2204.03776/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 7 Apr 2022.

## Builds on (most cited first, 8 of 8)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Kornia: an Open Source Differentiable Computer Vision Library for PyTorch](https://mlsanity.com/paper/1910.02190/) (2019)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [A Generalization of Otsu's Method and Minimum Error Thresholding](https://mlsanity.com/paper/2007.07350/) (2020)
- [Why Do Self-Supervised Models Transfer? Investigating the Impact of Invariance on Downstream Tasks](https://mlsanity.com/paper/2111.11398/) (2021)

## Built on by (most cited first, 10 of 10)

- [Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks](https://mlsanity.com/paper/2303.15127/) (2023)
- [Exploring Image Augmentations for Siamese Representation Learning with Chest X-Rays](https://mlsanity.com/paper/2301.12636/) (2023)
- [Writer Retrieval and Writer Identification in Greek Papyri](https://mlsanity.com/paper/2212.07664/) (2022)
- [Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networks](https://mlsanity.com/paper/2211.16098/) (2022)
- [Feature Mixing for Writer Retrieval and Identification on Papyri Fragments](https://mlsanity.com/paper/2306.12939/) (2023)
- [Label Augmentation for Neural Networks Robustness](https://mlsanity.com/paper/2408.01977/) (2024)
- [Efficient Annotation of Medieval Charters](https://mlsanity.com/paper/2306.14071/) (2023)
- [Temporal Modeling of Optically Variable Devices in Identity Documents](https://mlsanity.com/paper/2607.06408/) (2026)
- [TextileNet: Towards Zero-shot Text-style Segmentation of Manuscripts](https://mlsanity.com/paper/2607.09299/) (2026)
- [GeoPose: Patient-agnostic CTA-to-DSA registration through projection-space calibration](https://mlsanity.com/paper/2608.16600/) (2026)

## Abstract (arXiv)

We propose the use of fractals as a means of efficient data augmentation. Specifically, we employ plasma fractals for adapting global image augmentation transformations into continuous local transforms. We formulate the diamond square algorithm as a cascade of simple convolution operations allowing efficient computation of plasma fractals on the GPU. We present the TorMentor image augmentation framework that is totally modular and deterministic across images and point-clouds. All image augmentation operations can be combined through pipelining and random branching to form flow networks of arbitrary width and depth. We demonstrate the efficiency of the proposed approach with experiments on document image segmentation (binarization) with the DIBCO datasets. The proposed approach demonstrates superior performance to traditional image augmentation techniques. Finally, we use extended synthetic binary text images in a self-supervision regiment and outperform the same model when trained with limited data and simple extensions.