Comparer des méthodes

	Apprentissage par peu d'exemples régularisé	Semi-supervised Few-shot Learning
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2016-2020	2018
Auteur d'origine	Multiple (Chen et al., Tian et al., Snell et al., and others)	Ren, M. et al. (ICLR 2018); builds on Finn et al. (MAML, 2017)
Type	Meta-learning framework with explicit regularization	Meta-learning with unlabeled auxiliary data
Source fondatrice	Chen, W., Liu, Y., Kira, Z., Wang, Y. F., & Huang, J. (2019). A Closer Look at Few-Shot Classification. International Conference on Learning Representations (ICLR).	Ren, M., Triantafillou, E., Ravi, S., Snell, J., Swersky, K., Tenenbaum, J. B., Larochelle, H., & Zemel, R. S. (2018). Meta-learning for semi-supervised few-shot classification. In International Conference on Learning Representations (ICLR 2018).
Alias	FSL with regularization, regularized meta-learning, few-shot learning with regularization, regularized episodic learning	SS-FSL, semi-supervised meta-learning, few-shot learning with unlabeled data, low-label few-shot learning
Apparentées	5	4
Résumé	Regularized few-shot learning augments standard few-shot learning pipelines with explicit regularization mechanisms — such as weight decay, dropout, data augmentation, label smoothing, or manifold constraints — to reduce overfitting to the tiny support sets that define each episode. This produces more generalizable models when only one to thirty labeled examples per class are available.	Semi-supervised Few-shot Learning (SS-FSL) trains models to classify new classes from only a handful of labeled examples per class, while simultaneously leveraging a pool of unlabeled data to enrich class representations. By combining meta-learning episodes with soft pseudo-label assignment for unlabeled samples, it achieves notably higher accuracy than purely supervised few-shot methods when abundant unlabeled data is available.