방법 비교

	설명 가능한 비전 트랜스포머(Explainable Vision Transformer)	Semantic segmentation
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	2021	2015
창시자	Chefer, H., Gur, S., & Wolf, L. (attribution framework); Dosovitskiy et al. (base ViT)	Long, J., Shelhamer, E., & Darrell, T.
유형	Post-hoc explainability applied to Vision Transformer	Dense prediction / pixel-wise classification
원전	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.	Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440.
별칭	XViT, Interpretable ViT, Explainable ViT, Transparent Vision Transformer	pixel-wise classification, scene parsing, dense labeling, semantic scene segmentation
관련	5	5
요약	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.	Semantic segmentation assigns a class label to every pixel in an image, producing a dense, category-annotated map of the scene. Unlike object detection, which draws bounding boxes, it delineates the exact spatial extent of each class, making it indispensable in medical imaging, autonomous driving, satellite analysis, and any task where precise region boundaries matter.