手法を比較

	ファインチューニングされたVision Transformer	ビジョントランスフォーマー
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2020-2021	2021
提唱者	Dosovitskiy, A. et al. (Google Brain)	Dosovitskiy, A. et al.
種類	Transfer learning / fine-tuning of attention-based image model	Transformer architecture for images (self-attention over patches)
原典	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).	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
別名	Fine-Tuned ViT, ViT fine-tuning, Vision Transformer transfer learning, ViT downstream adaptation	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
関連	5	5
概要	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.	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).