Сравнение методов

	Самообучающаяся классификация изображений	Перенос обучения
Область	Глубокое обучение	Машинное обучение
Семейство	Machine learning	Machine learning
Год появления	2018–2020	2010 (formalized); 1990s (early roots)
Автор метода	Chen et al. (SimCLR); He et al. (MoCo); Grill et al. (BYOL); Caron et al. (DINO)	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Тип	Pretraining + fine-tuning paradigm	Learning paradigm
Основополагающий источник	Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119, 1597–1607.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Другие названия	SSL image classification, contrastive visual representation learning, self-supervised visual learning, unsupervised pretraining for image classification	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Связанные	4	3
Сводка	Self-supervised image classification trains a deep visual encoder on large unlabeled image datasets by solving proxy tasks — such as predicting which two augmented views of the same image are similar — and then fine-tunes only a lightweight classifier head on labeled examples. Pioneered by frameworks such as SimCLR and MoCo around 2020, it drastically reduces the need for expensive manual annotation while achieving accuracy rivaling fully supervised models.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.