VoronoiPatches: Evaluating a New Data Augmentation Method

Illium, Steffen; Griffin, Gretchen; Kölle, Michael; Zorn, Maximilian ; Nüßlein, Jonas und Linnhoff-Popien, Claudia (2023): VoronoiPatches: Evaluating a New Data Augmentation Method. ICAART 2023: 15th International Conference on Agents and Artificial Intelligence, Lisbon, Portugal, 22. - 24. Februar 2023. Rocha, Ana Paula; Steels, Luc und Herik, Jaap van den (Hrsg.): In: Proceedings of the 15th International Conference on Agents and Artificial Intelligence - (Volume 3), Setúbal: SciTePress. S. 350-357

Abstract

Overfitting is a problem in Convolutional Neural Networks (CNN) that causes poor generalization of models on unseen data. To remediate this problem, many new and diverse data augmentation (DA) methods have been proposed to supplement or generate more training data, and thereby increase its quality. In this work, we propose a new DA algorithm: VoronoiPatches (VP). We primarily utilize non-linear re-combination of information within an image, fragmenting and occluding small information patches. Unlike other DA methods, VP uses small convex polygon-shaped patches in a random layout to transport information around within an image. In our experiments, VP outperformed current DA methods regarding model variance and overfitting tendencies. We demonstrate DA utilizing non-linear re-combination of information within images, and non-orthogonal shapes and structures improves CNN model robustness on unseen data.

• Dokumententyp: Konferenzbeitrag (Paper)
• Fakultät: Mathematik, Informatik und Statistik > Informatik
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• ISBN: 978-989-758-623-1
• ISSN: 2184-433X
• Ort: Setúbal