Methoden vergelijken

	Data-augmentatie	Generatief Adversarieel Netwerk	Out-of-Distribution Detectie
Vakgebied	Deep learning	Deep learning	Machine learning
Familie	Machine learning	Machine learning	Machine learning
Jaar van ontstaan	2019	2014	2017
Grondlegger	Connor Shorten & Taghi Khoshgoftaar	Goodfellow, I. et al.	Hendrycks & Gimpel
Type	Regularization / data preprocessing technique	Generative deep learning (adversarial two-network game)	Reliability and safety method for neural networks
Oorspronkelijke bron	Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6, 60.	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.	Hendrycks, D., & Gimpel, K. (2017). A baseline for detecting misclassified and out-of-distribution examples in neural networks. International Conference on Learning Representations.
Aliassen	Training Data Augmentation, Image Augmentation, Veri Artırma, Synthetic Data Augmentation	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network	OOD Detection, Novelty Detection, Open-Set Recognition, Dağılım Dışı Tespit
Verwant	2	4	3
Samenvatting	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.	A Generative Adversarial Network (GAN), introduced by Ian Goodfellow and colleagues in 2014, produces realistic synthetic data through the competition of two neural networks — a generator and a discriminator. It is widely used for image synthesis, data augmentation, and distribution estimation.	Out-of-Distribution (OOD) detection is a set of techniques that identify when a deployed machine learning model receives inputs that differ significantly from its training data distribution. Introduced as a formal problem by Hendrycks and Gimpel in 2017, these methods enable models to flag unfamiliar inputs rather than silently produce unreliable predictions, making them foundational to trustworthy and safe AI deployment in high-stakes domains.