手法を比較

	説明可能なVision Transformer	画像分類
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2021	2012 (deep CNN era); conceptual roots 1989 (LeCun)
提唱者	Chefer, H., Gur, S., & Wolf, L. (attribution framework); Dosovitskiy et al. (base ViT)	Krizhevsky, A.; Sutskever, I.; Hinton, G. E.
種類	Post-hoc explainability applied to Vision Transformer	Supervised classification task
原典	Chefer, H., Gur, S., & Wolf, L. (2021). Transformer interpretability beyond attention visualization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 782–791.	Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems (NeurIPS), 25, 1097–1105.
別名	XViT, Interpretable ViT, Explainable ViT, Transparent Vision Transformer	visual classification, image recognition, CNN-based classification, visual categorization
関連	5	5
概要	Explainable Vision Transformer combines the strong image-recognition performance of Vision Transformers (ViT) with attribution techniques — such as relevance propagation, attention rollout, or gradient-weighted attention — that highlight which image regions drive each prediction. The approach enables researchers and practitioners to audit model decisions and satisfy transparency requirements without sacrificing accuracy.	Image classification is the task of assigning a single semantic label to an entire image from a fixed set of categories. Modern approaches rely on deep convolutional neural networks (CNNs) or Vision Transformers (ViTs) trained end-to-end on large labeled datasets such as ImageNet, achieving superhuman accuracy on many benchmarks and underpinning applications from medical imaging to autonomous vehicles.