Comparer des méthodes

	Apprentissage à peu d'exemples	Apprentissage métrique
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2011–2017	2003 (foundational); refined 2009 (LMNN)
Auteur d'origine	Lake, B. M.; Vinyals, O.; Finn, C. et al.	Xing, E. P.; Jordan, M. I.; Russell, S.; Ng, A. Y.
Type	Meta-learning / low-data learning paradigm	Representation learning / supervised distance optimization
Source fondatrice	Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., & Kavukcuoglu, K. (2016). Matching Networks for One Shot Learning. Advances in Neural Information Processing Systems (NeurIPS), 29.	Xing, E. P., Jordan, M. I., Russell, S., & Ng, A. Y. (2003). Distance metric learning with application to clustering with side-information. In Advances in Neural Information Processing Systems (NIPS), 16, 505–512.
Alias	FSL, low-shot learning, k-shot learning, meta-learning for few examples	Distance Metric Learning, Similarity Learning, DML, Representation Learning via Distance
Apparentées	4	5
Résumé	Few-shot learning is a machine learning paradigm that trains models to recognize new classes or solve new tasks from only a handful of labeled examples — typically one to five — by leveraging prior knowledge acquired from a large, related training distribution. It is especially relevant in domains where labeling is expensive, scarce, or structurally limited.	Metric learning is a machine-learning framework that trains a distance or similarity function from data so that semantically similar examples end up close together in the learned space while dissimilar examples are pushed apart. Unlike fixed distances such as Euclidean, the learned metric adapts to the structure of the task, making downstream classifiers, clusterers, and retrieval systems significantly more accurate.