Порівняння методів

	Згорточна нейронна мережа із самоконтролем	Напівкерована згорткова нейронна мережа
Галузь	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning
Рік появи	2018–2020	2013–2017
Автор методу	LeCun, Y. (CNN backbone); Chen et al. and He et al. (self-supervised visual frameworks)	Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others)
Тип	Self-supervised deep learning	Semi-supervised deep learning
Основоположне джерело	Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning (ICML 2020), PMLR 119, 1597–1607.	Lee, D.-H. (2013). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. ICML Workshop on Challenges in Representation Learning.
Інші назви	Self-supervised CNN, SSL-CNN, contrastive CNN, pretext-task CNN	SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN
Пов'язані	5	5
Підсумок	A self-supervised convolutional neural network (CNN) learns powerful visual representations from unlabeled images by solving pretext tasks — such as contrastive instance discrimination or masked-patch prediction — and then fine-tunes on a small labeled set. This approach dramatically reduces dependence on large annotated datasets while preserving the spatial feature-extraction strengths of convolutional architectures.	A Semi-supervised CNN trains a convolutional network on a small labeled image set and a larger pool of unlabeled images simultaneously, using techniques such as pseudo-labeling and consistency regularization to extract supervisory signal from unlabeled data. This strategy closes much of the performance gap caused by scarce annotations without requiring additional human labeling effort.