Comparer des méthodes

	Apprentissage métrique	Apprentissage à peu d'exemples
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2003 (foundational); refined 2009 (LMNN)	2011–2017
Auteur d'origine	Xing, E. P.; Jordan, M. I.; Russell, S.; Ng, A. Y.	Lake, B. M.; Vinyals, O.; Finn, C. et al.
Type	Representation learning / supervised distance optimization	Meta-learning / low-data learning paradigm
Source fondatrice	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.	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.
Alias	Distance Metric Learning, Similarity Learning, DML, Representation Learning via Distance	FSL, low-shot learning, k-shot learning, meta-learning for few examples
Apparentées	5	4
Résumé	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.	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.