Сравнение методов

	Самообучающееся активное обучение	Активное обучение
Область	Машинное обучение	Машинное обучение
Семейство	Machine learning	Machine learning
Год появления	2020–2021	2009
Автор метода	Bengar et al. and concurrent works (multiple groups)	Burr Settles
Тип	Hybrid active-learning and self-supervised pre-training framework	Interactive supervised learning framework
Основополагающий источник	Bengar, J. Z., van de Weijer, J., Twardowski, B., & Raducanu, B. (2021). Reducing Label Effort: Self-Supervised Meets Active Learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 1631–1639.	Settles, B. (2009). Active learning literature survey. University of Wisconsin-Madison Computer Sciences Technical Report 1648.
Другие названия	SSL-AL, self-supervised active learning, semi-supervised active learning with self-supervision, label-efficient self-supervised learning	Query Learning, Optimal Experimental Design (ML context), Pool-Based Active Learning, Aktif Öğrenme
Связанные	5	2
Сводка	Self-supervised Active Learning (SSL-AL) is a label-efficient machine-learning paradigm that pre-trains a model on unlabeled data using self-supervised objectives, then strategically queries a human oracle for the most informative labels using an active-learning acquisition function. The result is strong predictive performance with a fraction of the annotation cost required by fully supervised approaches.	Active learning is an iterative machine-learning paradigm in which a learning algorithm selectively queries an oracle — typically a human annotator — for labels on the most informative unlabeled examples. Formalized by Burr Settles in his seminal 2009 literature survey, active learning addresses the practical bottleneck of annotation cost by achieving high model accuracy with far fewer labeled examples than passive supervised learning requires.