EUVIMEDEUVIMED entdecken
Crossref

Improving CIFAR-10 Image Classification with a Modified ResNet-18 and Advanced Data Augmentation Strategies

Israa Shihab Ahmed

Journal of Informatics and Advanced Data Science · 21.04.2026 · 1 (01) · 1-15

DOI: 10.66849/jiads.v1i0.6 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Informatics and Advanced Data Science, online erschienen am 21.04.2026. Verfasst von Israa Shihab Ahmed.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image classification tasks on low‑resolution datasets such as CIFAR‑10 involve significant challenges due to the limited spatial information available and the heightened risk of model overfitting when employing deep convolutional neural networks that are originally engineered for high‑resolution images. This paper presents an optimized deep learningsystem based on an adapted ResNet-18, that is, specifically designed to classify images efficiently on the CIFAR-10 dataset. To retain spatial resolution in 32x32 images, the standard 7x7 convolutional stem of ResNet -18 is replaced by a 3x3 convolutional layer and the opening max -pooling operation is not used. Also, in order to boost generalization, more powerful approach to data-augmentation that includes random cropping, horizontalflipping, AutoAugment policies and random erasing is carried out during the training. The AdamW optimiser, which includes label smoothing, is used to perform model optimisation, and cosine annealing learning-rate schedule used to ensure that the learning rate smoothly converges. The experimental findings indicate that the suggested method has a testaccuracy of 92.75 00 per cent on the CIFAR-10 dataset. The steady increase in the validation performance during all training epochs suggests high generalization ability. Therefore, the suggested framework provides a practical and efficient approach to classification performance improvement on low-resolution image datasets.

Zitieren

APA

Ahmed, I. S. (2026). Improving CIFAR-10 Image Classification with a Modified ResNet-18 and Advanced Data Augmentation Strategies. Journal of Informatics and Advanced Data Science, 1(01), 1-15. https://doi.org/10.66849/jiads.v1i0.6

Vancouver

Ahmed IS. Improving CIFAR-10 Image Classification with a Modified ResNet-18 and Advanced Data Augmentation Strategies. Journal of Informatics and Advanced Data Science. 2026;1(01):1-15. doi:10.66849/jiads.v1i0.6

BibTeX
@article{Ahmed2026,
  author = {Ahmed, Israa Shihab},
  title = {Improving CIFAR-10 Image Classification with a Modified ResNet-18 and Advanced Data Augmentation Strategies},
  journal = {Journal of Informatics and Advanced Data Science},
  year = {2026},
  volume = {1},
  number = {01},
  pages = {1--15},
  doi = {10.66849/jiads.v1i0.6}
}
Kostenlos starten →