方法对比

	自监督图像分类	Vision 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
提出者	Chen et al. (SimCLR); He et al. (MoCo); Grill et al. (BYOL); Caron et al. (DINO)	Dosovitskiy, A. et al.
类型	Pretraining + fine-tuning paradigm	Transformer architecture for images (self-attention over patches)
开创性文献	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.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
别名	SSL image classification, contrastive visual representation learning, self-supervised visual learning, unsupervised pretraining for image classification	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
相关	4	5
摘要	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.	The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs).