TorMentor: Deterministic dynamic-path, data augmentations with fractals
Nicolaou A, Christlein V, Riba E, Shi J, Vogeler G, Seuret M (2022)
Publication Type: Conference contribution
Publication year: 2022
Publisher: IEEE Computer Society
Book Volume: 2022-June
Pages Range: 2706-2710
Conference Proceedings Title: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Event location: New Orleans, LA
ISBN: 9781665487399
DOI: 10.1109/CVPRW56347.2022.00305
Open Access Link: https://openaccess.thecvf.com/content/CVPR2022W/ECV/papers/Nicolaou_TorMentor_Deterministic_Dynamic-Path_Data_Augmentations_With_Fractals_CVPRW_2022_paper.pdf
Abstract
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.
Authors with CRIS profile
Vincent Christlein
Lehrstuhl für Informatik 5 (Mustererkennung)
Mathias Seuret
Lehrstuhl für Informatik 5 (Mustererkennung)
Involved external institutions
Austria (AT)How to cite
APA:
Nicolaou, A., Christlein, V., Riba, E., Shi, J., Vogeler, G., & Seuret, M. (2022). TorMentor: Deterministic dynamic-path, data augmentations with fractals. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (pp. 2706-2710). New Orleans, LA, US: IEEE Computer Society.
MLA:
Nicolaou, Anguelos, et al. "TorMentor: Deterministic dynamic-path, data augmentations with fractals." Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022, New Orleans, LA IEEE Computer Society, 2022. 2706-2710.
BibTeX: Download