方法对比

	半监督视觉变换器	自监督视觉Transformer
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2021–2022	2021–2022
提出者	Dosovitskiy et al. (ViT); semi-supervised extensions by multiple groups (2021–2023)	Caron et al. (DINO); He et al. (MAE)
类型	Semi-supervised deep learning for image understanding	Self-supervised pre-training for vision transformers
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).	Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging Properties in Self-Supervised Vision Transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 9650–9660.
别名	Semi-supervised ViT, SSL-ViT, Semi-supervised Patch-based Transformer, Semi-supervised Self-Attention Image Model	SSL-ViT, self-supervised ViT, unsupervised ViT pre-training, vision transformer self-supervised pre-training
相关	6	4
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.	Self-supervised Vision Transformer (SSL-ViT) applies self-supervised pre-training objectives — such as masked patch prediction (MAE) or self-distillation with no labels (DINO) — to the Vision Transformer architecture, enabling powerful visual representations to be learned from large unlabeled image corpora before any task-specific fine-tuning.