Augmented COVID-19 CT images with CUTMIX, CUTOUT, and MIXUP Data Augmentation

This dataset consists of 30,000 augmented COVID-19 CT images generated from CUTMIX (Yun et al., 2019), CUTOUT (DeVries & Taylor, 2017), and MIXUP (Zhang et al., 2018) data augmentation techniques. The COVID-19 CT images are acquired from multiple publicly available sources (Morozov et al., 2020; Rahimzadeh et al., 2021; Maftouni et al., 2021).

References
DeVries, T., & Taylor, G. W. (2017). Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552

Maftouni, M., Law, A.C, Shen, B., Zhou, Y., Yazdi, N., & Kong, Z.J. (2021). A Robust Ensemble-Deep Learning Model for COVID-19 Diagnosis based on an Integrated CT Scan Images Database. In Proceedings of the 2021 Industrial and Systems Engineering Conference (pp. 632-637). Institute of Industrial and Systems Engineers.

Morozov, P., Andreychenko, A. E., et al. (2020). MosMedData: Chest CT Scans With COVID19 Related Findings Dataset. arXiv preprint arXiv: 2005.06465.

Rahimzadeh, M., Attar, A., & Sakhaei S. (2021). A fully automated deep learning-based network for detecting COVID-19 from a new and large lung CT scan dataset. Biomedical Signal Processing and Control, 68, pp. 102588.

Yun, S., Han, D., Oh, S. J., Chun, S., Choe, J., & Yoo, Y. (2019). CutMix: Regularization strategy to train strong classifiers with localizable features. arXiv preprint arXiv:1905.04899

Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2018). Mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412