Сравнение методов

	Самообучение с учителем	Перенос обучения
Область	Машинное обучение	Машинное обучение
Семейство	Machine learning	Machine learning
Год появления	2018–2020	2010 (formalized); 1990s (early roots)
Автор метода	LeCun, Y. and community (formalized ~2018–2020)	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Тип	Representation learning paradigm	Learning paradigm
Основополагающий источник	LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Другие названия	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Связанные	3	3
Сводка	Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples.	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.