方法对比

	半监督视觉变换器	半监督卷积神经网络
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2021–2022	2013–2017
提出者	Dosovitskiy et al. (ViT); semi-supervised extensions by multiple groups (2021–2023)	Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others)
类型	Semi-supervised deep learning for image understanding	Semi-supervised deep learning
开创性文献	Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations (ICLR 2021).	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.
别名	Semi-supervised ViT, SSL-ViT, Semi-supervised Patch-based Transformer, Semi-supervised Self-Attention Image Model	SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN
相关	6	5
摘要	Semi-supervised Vision Transformer applies the patch-based self-attention architecture of ViT to settings where only a fraction of images are labeled, exploiting large unlabeled corpora through pseudo-labeling, consistency regularization, or self-supervised pretext tasks before fine-tuning on the small labeled set. This approach achieves near-supervised accuracy even when labeled images are scarce.	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.