So sánh phương pháp

	Học chuyển giao tự giám sát	Học tăng cường tự giám sát
Lĩnh vực	Học máy	Học máy
Họ	Machine learning	Machine learning
Năm ra đời	2018–2020 (modern consolidation)	2018–2020
Người khởi xướng	LeCun, Y. (concept); Devlin et al. (BERT, NLP); Chen et al. (SimCLR, vision)	LeCun, Y. and community (formalized ~2018–2020)
Loại	Learning paradigm (self-supervised pre-training + fine-tuning)	Representation 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.	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	self-supervised pre-training, SSL-based transfer learning, representation transfer from self-supervised models, contrastive pre-training with transfer	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Liên quan	6	3
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.	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.