So sánh phương pháp

	Học chuyển giao tự giám sát	Học bán giám sát
Lĩnh vực	Học máy	Học máy
Họ	Machine learning	Machine learning
Năm ra đời	2018–2020 (modern consolidation)	1970s–2006 (formalized)
Người khởi xướng	LeCun, Y. (concept); Devlin et al. (BERT, NLP); Chen et al. (SimCLR, vision)	Vapnik, V. N. and others (community of researchers, 1970s–2000s)
Loại	Learning paradigm (self-supervised pre-training + fine-tuning)	Learning paradigm
Công trình gốc	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.	Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9
Tên gọi khác	self-supervised pre-training, SSL-based transfer learning, representation transfer from self-supervised models, contrastive pre-training with transfer	SSL, semi-supervised machine learning, transductive learning, label-efficient learning
Liên quan	6	5
Tóm tắt	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.	Semi-supervised learning (SSL) is a machine learning paradigm that trains models using a small set of labeled examples together with a much larger pool of unlabeled data. By leveraging the structure inherent in unlabeled data, SSL achieves accuracy closer to fully supervised models while requiring far fewer costly manual labels — making it practical when labeling is expensive, slow, or resource-constrained.