Comparer des méthodes

	Forêt aléatoire auto-supervisée	Apprentissage auto-supervisé
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2012–2022	2018–2020
Auteur d'origine	Lefortier, D. et al.; Criminisi, A. et al. (semi-supervised RF lineage)	LeCun, Y. and community (formalized ~2018–2020)
Type	Semi-supervised ensemble (self-supervised pretext task + RF)	Representation learning paradigm
Source fondatrice	Lefortier, D., Chitta, K., & Agrawal, P. (2022). Self-supervised random forests. arXiv:2204.01430.	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	SSL-RF, self-supervised RF, self-supervised ensemble forest, unsupervised random forest with self-labeling	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Apparentées	6	3
Résumé	Self-supervised Random Forest (SSL-RF) extends the classic random forest to settings where labeled examples are scarce. The forest is first trained using automatically generated pseudo-labels derived from a self-supervised pretext task — such as predicting data transformations or masked features — and then refined on whatever true labels are available, marrying the label-efficiency of self-supervised learning with the robustness of ensemble trees.	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.