手法を比較

	ファインチューニングされた拡散モデル	ファインチューニングされたVision Transformer
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2020–2023	2020-2021
提唱者	Ho, J., Jain, A., Abbeel, P. (base DDPM); Ruiz et al. (DreamBooth fine-tuning paradigm)	Dosovitskiy, A. et al. (Google Brain)
種類	Generative model (fine-tuned via subject-specific or domain-specific data)	Transfer learning / fine-tuning of attention-based image model
原典	Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2023). DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 22500–22510.	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).
別名	DDPM fine-tuning, diffusion model adaptation, personalized diffusion model, subject-driven diffusion fine-tuning	Fine-Tuned ViT, ViT fine-tuning, Vision Transformer transfer learning, ViT downstream adaptation
関連	5	5
概要	A fine-tuned diffusion model adapts a large pretrained denoising diffusion model — such as Stable Diffusion or DALL-E — to a specific subject, style, or domain by continuing training on a small curated dataset. Techniques such as DreamBooth, textual inversion, and LoRA make this adaptation feasible on consumer hardware while preserving general generative capability.	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.