方法对比

	LoRA 和 PEFT	Vision Transformer
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2022	2021
提出者	Hu, E. J. et al.; Lester, B. et al.	Dosovitskiy, A. et al.
类型	Parameter-efficient fine-tuning of large pretrained models	Transformer architecture for images (self-attention over patches)
开创性文献	Hu, E. J. et al. (2022). LoRA: Low-Rank Adaptation of Large Language Models. ICLR.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
别名	LoRA ve PEFT — Parametre Verimli İnce Ayar, Low-Rank Adaptation, parameter-efficient fine-tuning, prefix tuning	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
相关	5	5
摘要	LoRA (Low-Rank Adaptation), introduced by Hu et al. in 2022, and the broader family of parameter-efficient fine-tuning (PEFT) methods adapt large pretrained language models to new tasks by training only a small number of extra parameters instead of every weight in the model. This makes fine-tuning possible with far less GPU memory and compute while leaving the original model largely untouched.	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).