Porównaj metody

	Explainable Vision Transformer	Vision Transformer
Dziedzina	Uczenie głębokie	Uczenie głębokie
Rodzina	Machine learning	Machine learning
Rok powstania	2021	2021
Twórca	Chefer, H., Gur, S., & Wolf, L. (attribution framework); Dosovitskiy et al. (base ViT)	Dosovitskiy, A. et al.
Typ	Post-hoc explainability applied to Vision Transformer	Transformer architecture for images (self-attention over patches)
Źródło pierwotne	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.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Inne nazwy	XViT, Interpretable ViT, Explainable ViT, Transparent Vision Transformer	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Pokrewne	5	5
Podsumowanie	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.	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).