手法を比較

	ビジョントランスフォーマー	サポートベクターマシン（分類）
分野	深層学習	機械学習
系統	Machine learning	Machine learning
提唱年	2021	1995
提唱者	Dosovitskiy, A. et al.	Cortes, C. & Vapnik, V.
種類	Transformer architecture for images (self-attention over patches)	Maximum-margin classifier (kernel method)
原典	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.	Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297.
別名	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images	Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
関連	5	5
概要	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).	The Support Vector Machine, introduced by Corinna Cortes and Vladimir Vapnik in 1995, is a classifier that finds the optimal separating hyperplane between classes in a high-dimensional space. It chooses the boundary that leaves the widest possible margin to the nearest training points, which makes its decisions robust on new data.