手法を比較

	自己教師あり畳み込みニューラルネットワーク	半教師あり畳み込みニューラルネットワーク
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2018–2020	2013–2017
提唱者	LeCun, Y. (CNN backbone); Chen et al. and He et al. (self-supervised visual frameworks)	Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others)
種類	Self-supervised deep learning	Semi-supervised deep learning
原典	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.
別名	Self-supervised CNN, SSL-CNN, contrastive CNN, pretext-task CNN	SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN
関連	5	5
概要	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.