Comparer des méthodes

	Apprentissage actif avec apprentissage auto-supervisé	Apprentissage à peu d'exemples
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2020-2022	2011–2017
Auteur d'origine	Multiple authors (active learning + SSL integration, 2020s)	Lake, B. M.; Vinyals, O.; Finn, C. et al.
Type	Hybrid learning paradigm	Meta-learning / low-data learning paradigm
Source fondatrice	Bengar, J. Z., van de Weijer, J., Fuentes, L. L., & Raducanu, B. (2022). Class-Balanced Active Learning for Image Classification. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 3082–3091.	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.
Alias	AL-SSL, active self-supervised learning, self-supervised active learning, query-based self-supervised learning	FSL, low-shot learning, k-shot learning, meta-learning for few examples
Apparentées	6	4
Résumé	Active learning combined with self-supervised learning leverages unlabeled data through self-supervised pre-training to build rich representations, then uses an active query strategy to select the most informative examples for human annotation, maximizing model performance under a tight labeling budget. This hybrid approach is especially powerful when labeled data is scarce but large unlabeled pools exist.	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.