TorMentor: Deterministic dynamic-path, data augmentations with fractals
This work addresses data augmentation efficiency for image and point-cloud processing, though it appears incremental as it builds on existing fractal methods.
The authors tackled the problem of efficient data augmentation by using plasma fractals to create continuous local transforms, resulting in superior performance over traditional techniques on document image segmentation tasks with DIBCO datasets and outperforming models trained with limited data in self-supervision.
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.