方法对比

	自监督卷积神经网络	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	2018–2020	2021–2022
提出者	LeCun, Y. (CNN backbone); Chen et al. and He et al. (self-supervised visual frameworks)	Caron et al. (DINO); He et al. (MAE)
类型	Self-supervised deep learning	Self-supervised pre-training for vision transformers
开创性文献	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.	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	Self-supervised CNN, SSL-CNN, contrastive CNN, pretext-task CNN	SSL-ViT, self-supervised ViT, unsupervised ViT pre-training, vision transformer self-supervised pre-training
相关	5	4
摘要	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.	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.