Porównaj metody

	Samouczenie się klasyfikacji obrazów	Uczenie transferowe
Dziedzina	Uczenie głębokie	Uczenie maszynowe
Rodzina	Machine learning	Machine learning
Rok powstania	2018–2020	2010 (formalized); 1990s (early roots)
Twórca	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)
Typ	Pretraining + fine-tuning paradigm	Learning paradigm
Źródło pierwotne	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.
Inne nazwy	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
Pokrewne	4	3
Podsumowanie	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.