EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RSMDA: Random Slices Mixing Data Augmentation

Teerath Kumar, Alessandra Mileo, Rob Brennan, Malika Bendechache

Applied Sciences · 29.01.2023 · 13 (3) · 1711

DOI: 10.3390/app13031711 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 29.01.2023. Verfasst von Teerath Kumar und 3 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science Foundation Ireland, Insight SFI Research Centre for Data Analytics, Lero SFI Centre for Software.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Advanced data augmentation techniques have demonstrated great success in deep learning algorithms. Among these techniques, single-image-based data augmentation (SIBDA), in which a single image’s regions are randomly erased in different ways, has shown promising results. However, randomly erasing image regions in SIBDA can cause a loss of the key discriminating features, consequently misleading neural networks and lowering their performance. To alleviate this issue, in this paper, we propose the random slices mixing data augmentation (RSMDA) technique, in which slices of one image are placed onto another image to create a third image that enriches the diversity of the data. RSMDA also mixes the labels of the original images to create an augmented label for the new image to exploit label smoothing. Furthermore, we propose and investigate three strategies for RSMDA: (i) the vertical slices mixing strategy, (ii) the horizontal slices mixing strategy, and (iii) a random mix of both strategies. Of these strategies, the horizontal slice mixing strategy shows the best performance. To validate the proposed technique, we perform several experiments using different neural networks across four datasets: fashion-MNIST, CIFAR10, CIFAR100, and STL10. The experimental results of the image classification with RSMDA showed better accuracy and robustness than the state-of-the-art (SOTA) single-image-based and multi-image-based methods. Finally, class activation maps are employed to visualize the focus of the neural network and compare maps using the SOTA data augmentation methods.

Förderung

  • Science Foundation Ireland
  • Insight SFI Research Centre for Data Analytics
  • Lero SFI Centre for Software
  • ADAPT SFI Research Centre for AI-Driven Digital Content Technology

Zitieren

APA

Kumar, T., Mileo, A., Brennan, R., & Bendechache, M. (2023). RSMDA: Random Slices Mixing Data Augmentation. Applied Sciences, 13(3), 1711. https://doi.org/10.3390/app13031711

Vancouver

Kumar T, Mileo A, Brennan R, Bendechache M. RSMDA: Random Slices Mixing Data Augmentation. Applied Sciences. 2023;13(3):1711. doi:10.3390/app13031711

BibTeX
@article{Kumar2023,
  author = {Kumar, Teerath and Mileo, Alessandra and Brennan, Rob and Bendechache, Malika},
  title = {RSMDA: Random Slices Mixing Data Augmentation},
  journal = {Applied Sciences},
  year = {2023},
  volume = {13},
  number = {3},
  pages = {1711},
  doi = {10.3390/app13031711}
}
Kostenlos starten →