手法を比較

	弱教師あり畳み込みニューラルネットワーク	自己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	2015–2016	2018–2020
提唱者	Oquab, M. et al.; Zhou, B. et al.	LeCun, Y. (CNN backbone); Chen et al. and He et al. (self-supervised visual frameworks)
種類	Weakly supervised deep learning	Self-supervised deep learning
原典	Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2921–2929.	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.
別名	WS-CNN, weakly supervised CNN, CNN with weak labels, CNN with noisy labels	Self-supervised CNN, SSL-CNN, contrastive CNN, pretext-task CNN
関連	5	5
概要	A weakly supervised CNN is a convolutional neural network trained with incomplete, coarse, or noisy annotations instead of full pixel-level or bounding-box labels. Typical weak labels include image-level class tags, partial annotations, or crowd-sourced noisy labels. The model learns to classify and often to roughly localize objects using these cheaper, lower-quality supervision signals.	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.