방법 비교

	전이 학습	퓨샷 학습	자기 지도 학습
분야	머신러닝	머신러닝	머신러닝
계열	Machine learning	Machine learning	Machine learning
기원 연도	2010 (formalized); 1990s (early roots)	2011–2017	2018–2020
창시자	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)	Lake, B. M.; Vinyals, O.; Finn, C. et al.	LeCun, Y. and community (formalized ~2018–2020)
유형	Learning paradigm	Meta-learning / low-data learning paradigm	Representation learning paradigm
원전	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.	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.	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/
별칭	TL, domain adaptation, fine-tuning, pre-trained model adaptation	FSL, low-shot learning, k-shot learning, meta-learning for few examples	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
관련	3	4	3
요약	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.	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.	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.