Võrdle meetodeid

	Pooltugevdatud väheste näidistega õppimine	Väheste näidistega õppimine
Valdkond	Masinõpe	Masinõpe
Perekond	Machine learning	Machine learning
Tekkeaasta	2018	2011–2017
Looja	Ren, M. et al. (ICLR 2018); builds on Finn et al. (MAML, 2017)	Lake, B. M.; Vinyals, O.; Finn, C. et al.
Tüüp	Meta-learning with unlabeled auxiliary data	Meta-learning / low-data learning paradigm
Algallikas	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).	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.
Rööpnimetused	SS-FSL, semi-supervised meta-learning, few-shot learning with unlabeled data, low-label few-shot learning	FSL, low-shot learning, k-shot learning, meta-learning for few examples
Seotud	4	4
Kokkuvõte	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.	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.