方法对比

	自监督迁移学习	少样本学习
领域	机器学习	机器学习
方法族	Machine learning	Machine learning
起源年份	2018–2020 (modern consolidation)	2011–2017
提出者	LeCun, Y. (concept); Devlin et al. (BERT, NLP); Chen et al. (SimCLR, vision)	Lake, B. M.; Vinyals, O.; Finn, C. et al.
类型	Learning paradigm (self-supervised pre-training + fine-tuning)	Meta-learning / low-data learning paradigm
开创性文献	Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119, 1597–1607.	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.
别名	self-supervised pre-training, SSL-based transfer learning, representation transfer from self-supervised models, contrastive pre-training with transfer	FSL, low-shot learning, k-shot learning, meta-learning for few examples
相关	6	4
摘要	Self-supervised transfer learning combines two powerful paradigms: a model first learns rich representations from unlabeled data using self-supervised pretext tasks, then those learned representations are transferred and fine-tuned on a downstream task with limited labeled data. This approach underlies landmark systems such as BERT in NLP and SimCLR and DINO in computer vision, dramatically reducing labeled-data requirements across many domains.	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.