Porovnať metódy

	Semi-supervidované učenie metrík	Few-shot Learning
Odbor	Strojové učenie	Strojové učenie
Rodina	Machine learning	Machine learning
Rok vzniku	2007–2008	2011–2017
Tvorca	Yeung, D.-Y. & Chang, H.; Davis, J. V. & Dhillon, I. S.	Lake, B. M.; Vinyals, O.; Finn, C. et al.
Typ	Hybrid supervised/unsupervised distance learning	Meta-learning / low-data learning paradigm
Pôvodný zdroj	Yeung, D.-Y., & Chang, H. (2007). A kernel approach for semi-supervised metric learning. IEEE Transactions on Neural Networks, 18(1), 141–149.	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.
Ďalšie názvy	SSML, semi-supervised distance learning, constrained metric learning, weakly supervised metric learning	FSL, low-shot learning, k-shot learning, meta-learning for few examples
Príbuzné	5	4
Zhrnutie	Semi-supervised metric learning learns a task-adapted distance function by combining a small set of labeled pairwise constraints — must-link and cannot-link pairs — with the geometric structure of a much larger pool of unlabeled data. The result is a Mahalanobis-style or kernel-based distance that reflects both supervision and data topology, improving downstream tasks such as nearest-neighbor classification and clustering.	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.