方法对比

	可解释视觉 Transformer	自监督视觉Transformer
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2021	2021–2022
提出者	Chefer, H., Gur, S., & Wolf, L. (attribution framework); Dosovitskiy et al. (base ViT)	Caron et al. (DINO); He et al. (MAE)
类型	Post-hoc explainability applied to Vision Transformer	Self-supervised pre-training for vision transformers
开创性文献	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.	Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging Properties in Self-Supervised Vision Transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 9650–9660.
别名	XViT, Interpretable ViT, Explainable ViT, Transparent Vision Transformer	SSL-ViT, self-supervised ViT, unsupervised ViT pre-training, vision transformer self-supervised pre-training
相关	5	4
摘要	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.	Self-supervised Vision Transformer (SSL-ViT) applies self-supervised pre-training objectives — such as masked patch prediction (MAE) or self-distillation with no labels (DINO) — to the Vision Transformer architecture, enabling powerful visual representations to be learned from large unlabeled image corpora before any task-specific fine-tuning.