Сравнение методов

	Метрическое обучение	Перенос обучения
Область	Машинное обучение	Машинное обучение
Семейство	Machine learning	Machine learning
Год появления	2003 (foundational); refined 2009 (LMNN)	2010 (formalized); 1990s (early roots)
Автор метода	Xing, E. P.; Jordan, M. I.; Russell, S.; Ng, A. Y.	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Тип	Representation learning / supervised distance optimization	Learning paradigm
Основополагающий источник	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.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Другие названия	Distance Metric Learning, Similarity Learning, DML, Representation Learning via Distance	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Связанные	5	3
Сводка	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.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.