方法对比

	半监督图像分类	自监督图像分类
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2013–2020	2018–2020
提出者	Lee, D.-H. (pseudo-label); Sohn et al. (FixMatch)	Chen et al. (SimCLR); He et al. (MoCo); Grill et al. (BYOL); Caron et al. (DINO)
类型	Semi-supervised deep learning	Pretraining + fine-tuning paradigm
开创性文献	Lee, D.-H. (2013). Pseudo-Label: The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks. ICML 2013 Workshop on Challenges in Representation Learning.	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.
别名	SSL image classification, semi-supervised CNN classification, pseudo-label image classification, label-efficient image classification	SSL image classification, contrastive visual representation learning, self-supervised visual learning, unsupervised pretraining for image classification
相关	5	4
摘要	Semi-supervised image classification trains deep neural networks on a small set of labeled images together with a much larger pool of unlabeled images. Techniques such as pseudo-labeling, consistency regularization, and confidence thresholding allow the model to leverage the structure of unlabeled data, dramatically reducing the need for expensive manual annotation while approaching fully-supervised accuracy.	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.