方法对比

	BERT微调	Vision Transformer
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2019	2021
提出者	Devlin, J. et al.	Dosovitskiy, A. et al.
类型	Transfer learning (fine-tuning a pre-trained transformer)	Transformer architecture for images (self-attention over patches)
开创性文献	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
别名	BERT İnce Ayar (Fine-Tuning), BERT ince ayar, fine-tuning BERT, transfer learning with BERT	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
相关	5	5
摘要	BERT fine-tuning, building on the BERT model introduced by Devlin and colleagues in 2019, re-trains a pre-trained BERT model on a small labelled dataset for a target task such as classification, named-entity recognition, or question answering. Through transfer learning it reaches high performance even with relatively little task-specific data.	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).