Comparer des méthodes

	Apprentissage métrique robuste	Apprentissage à peu d'exemples
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2009–2012	2011–2017
Auteur d'origine	Various (Weinberger, Saul, Schultz et al.; robust extensions by Shen, Cao and others, 2009–2012)	Lake, B. M.; Vinyals, O.; Finn, C. et al.
Type	Supervised/semi-supervised distance metric learning with robustness to noise and outliers	Meta-learning / low-data learning paradigm
Source fondatrice	Shen, C., Kim, J., Wang, L., & van den Hengel, A. (2012). Positive Semidefinite Metric Learning Using Boosting-like Algorithms. Journal of Machine Learning Research, 13, 1007–1036.	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	robust distance metric learning, noise-robust metric learning, outlier-robust similarity learning, robust DML	FSL, low-shot learning, k-shot learning, meta-learning for few examples
Apparentées	5	4
Résumé	Robust Metric Learning learns a Mahalanobis distance function from labeled or pairwise-constrained data while actively resisting the distortion caused by noisy labels, corrupted examples, or outliers. By replacing standard hinge or squared losses with robust alternatives and adding regularization, it produces a distance metric that generalises well even when the training set is imperfect — a common situation in real-world scientific and applied tasks.	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.