Comparer des méthodes

	Apprentissage par transfert semi-supervisé	Apprentissage auto-supervisé
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2010s	2018–2020
Auteur d'origine	Pan, S. J. & Yang, Q. (formalized); wider community	LeCun, Y. and community (formalized ~2018–2020)
Type	Hybrid learning paradigm	Representation learning paradigm
Source fondatrice	Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., & He, Q. (2021). A comprehensive survey on transfer learning. Proceedings of the IEEE, 109(1), 43–76.	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/
Alias	SSTL, semi-supervised domain adaptation, transfer learning with unlabeled data, few-label transfer learning	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Apparentées	4	3
Résumé	Semi-supervised Transfer Learning combines knowledge transferred from a richly labeled source domain with the structure of abundant unlabeled target-domain data, using only a small set of labeled target examples to achieve strong generalization where full annotation is scarce or expensive.	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.