方法对比

	迁移学习在图像分类中的应用	微调视觉Transformer
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2010–2012	2020-2021
提出者	Pan, S. J. & Yang, Q. (transfer learning framework); Krizhevsky, Sutskever & Hinton (deep CNN backbone)	Dosovitskiy, A. et al. (Google Brain)
类型	Transfer learning / supervised classification	Transfer learning / fine-tuning of attention-based image model
开创性文献	Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.	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. In International Conference on Learning Representations (ICLR 2021).
别名	pretrained CNN image classification, fine-tuned image classifier, domain-adapted image classifier, TL-IC	Fine-Tuned ViT, ViT fine-tuning, Vision Transformer transfer learning, ViT downstream adaptation
相关	4	5
摘要	Transfer Learning with Image Classification reuses a deep neural network backbone — typically a CNN or Vision Transformer — pretrained on a large dataset such as ImageNet, and adapts it to classify images in a new target domain. By inheriting general visual features from the source task, the approach achieves high accuracy with far fewer labeled images than training from scratch.	Fine-Tuned Vision Transformer adapts a large pre-trained ViT model — which splits images into fixed-size patches and processes them through self-attention layers — to a new image classification or recognition task using a relatively small labeled dataset. It achieves state-of-the-art accuracy in computer vision by leveraging rich representations learned during large-scale pre-training.