Porovnat metody

	Polosupervizované učení s malým počtem příkladů	Samoučící se učení
Obor	Strojové učení	Strojové učení
Rodina	Machine learning	Machine learning
Rok vzniku	2018	2018–2020
Tvůrce	Ren, M. et al. (ICLR 2018); builds on Finn et al. (MAML, 2017)	LeCun, Y. and community (formalized ~2018–2020)
Typ	Meta-learning with unlabeled auxiliary data	Representation learning paradigm
Původní zdroj	Ren, M., Triantafillou, E., Ravi, S., Snell, J., Swersky, K., Tenenbaum, J. B., Larochelle, H., & Zemel, R. S. (2018). Meta-learning for semi-supervised few-shot classification. In International Conference on Learning Representations (ICLR 2018).	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/
Další názvy	SS-FSL, semi-supervised meta-learning, few-shot learning with unlabeled data, low-label few-shot learning	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Příbuzné	4	3
Shrnutí	Semi-supervised Few-shot Learning (SS-FSL) trains models to classify new classes from only a handful of labeled examples per class, while simultaneously leveraging a pool of unlabeled data to enrich class representations. By combining meta-learning episodes with soft pseudo-label assignment for unlabeled samples, it achieves notably higher accuracy than purely supervised few-shot methods when abundant unlabeled data is available.	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.