So sánh phương pháp

	Học tăng cường bán giám sát với ít mẫu (Semi-supervised Few-shot Learning)	Học tăng cường tự giám sát
Lĩnh vực	Học máy	Học máy
Họ	Machine learning	Machine learning
Năm ra đời	2018	2018–2020
Người khởi xướng	Ren, M. et al. (ICLR 2018); builds on Finn et al. (MAML, 2017)	LeCun, Y. and community (formalized ~2018–2020)
Loại	Meta-learning with unlabeled auxiliary data	Representation learning paradigm
Công trình gốc	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/
Tên gọi khác	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
Liên quan	4	3
Tóm tắt	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.