So sánh phương pháp

	Tăng cường dữ liệu	Huấn luyện đối kháng
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2019	2018
Người khởi xướng	Connor Shorten & Taghi Khoshgoftaar	Aleksander Madry et al.
Loại	Regularization / data preprocessing technique	Robust optimization training procedure
Công trình gốc	Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6, 60.	Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2018). Towards deep learning models resistant to adversarial attacks. International Conference on Learning Representations (ICLR).
Tên gọi khác	Training Data Augmentation, Image Augmentation, Veri Artırma, Synthetic Data Augmentation	Min-Max Robust Training, PGD Adversarial Training, Robust Empirical Risk Minimization, Hasımsal Eğitim
Liên quan	2	3
Tóm tắt	Data augmentation is a family of techniques that artificially expands a training dataset by applying label-preserving transformations to existing samples. Originally systematized for image classification tasks, it is now applied broadly across vision, text, audio, and tabular domains. It emerged as a practical answer to the chronic scarcity of labeled data in supervised deep learning and remains a standard preprocessing step in modern neural network pipelines.	Adversarial Training is a robust optimization procedure for deep neural networks in which the model is trained not on clean data alone but on worst-case perturbed inputs crafted during training. Formalized by Madry et al. (2018) as a min-max saddle-point problem, the method uses Projected Gradient Descent (PGD) to generate strong adversarial examples within a bounded Lp perturbation set before each gradient update, forcing the network to learn decision boundaries that are stable under such perturbations.