EUVIMEDEUVIMED entdecken
Crossref

RandoMix: a mixed sample data augmentation method with multiple mixed modes

Xiaoliang Liu, Furao Shen, Jian Zhao, Changhai Nie

Multimedia Tools and Applications · 19.03.2024 · 84 (8) · 4343-4359

DOI: 10.1007/s11042-024-18868-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Multimedia Tools and Applications, online erschienen am 19.03.2024. Verfasst von Xiaoliang Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: the STI 2030-Major Projects of China, the National Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains. In this study, we introduce a novel mixed-sample data augmentation method called RandoMix. RandoMix is specifically designed to simultaneously address robustness and diversity challenges. It leverages a combination of linear and mask mixed modes, introducing flexibility in candidate selection and weight adjustments. We evaluate the effectiveness of RandoMix on diverse datasets, including CIFAR-10/100, Tiny-ImageNet, ImageNet, and Google Speech Commands. Our results demonstrate its superior erformance compared to existing techniques such as Mixup, CutMix, Fmix, and ResizeMix. Notably, RandoMix excels in enhancing model robustness against adversarial noise, natural noise, and sample occlusion. The comprehensive experimental results and insights into parameter tuning underscore the potential of RandoMix as a versatile and effective data augmentation method. Moreover, it seamlessly integrates into the training pipeline.

Förderung

  • the STI 2030-Major Projects of China
  • the National Science Foundation of China

Zitieren

APA

Liu, X., Shen, F., Zhao, J., & Nie, C. (2024). RandoMix: a mixed sample data augmentation method with multiple mixed modes. Multimedia Tools and Applications, 84(8), 4343-4359. https://doi.org/10.1007/s11042-024-18868-8

Vancouver

Liu X, Shen F, Zhao J, Nie C. RandoMix: a mixed sample data augmentation method with multiple mixed modes. Multimedia Tools and Applications. 2024;84(8):4343-4359. doi:10.1007/s11042-024-18868-8

BibTeX
@article{Liu2024,
  author = {Liu, Xiaoliang and Shen, Furao and Zhao, Jian and Nie, Changhai},
  title = {RandoMix: a mixed sample data augmentation method with multiple mixed modes},
  journal = {Multimedia Tools and Applications},
  year = {2024},
  volume = {84},
  number = {8},
  pages = {4343--4359},
  doi = {10.1007/s11042-024-18868-8}
}
Kostenlos starten →