방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 적대적 훈련× | 데이터 증강 (Data Augmentation)× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2018 | 2019 |
| 창시자≠ | Aleksander Madry et al. | Connor Shorten & Taghi Khoshgoftaar |
| 유형≠ | Robust optimization training procedure | Regularization / data preprocessing technique |
| 원전≠ | 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). link ↗ | Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6, 60. DOI ↗ |
| 별칭 | Min-Max Robust Training, PGD Adversarial Training, Robust Empirical Risk Minimization, Hasımsal Eğitim | Training Data Augmentation, Image Augmentation, Veri Artırma, Synthetic Data Augmentation |
| 관련≠ | 3 | 2 |
| 요약≠ | 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. | 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. |
| ScholarGate데이터셋 ↗ |
|
|