Сравнение методов

	Объяснимая семантическая сегментация	LIME: Локально-интерпретируемые модельно-агностические объяснения
Область	Глубокое обучение	Машинное обучение
Семейство	Machine learning	Machine learning
Год появления	2019–2021	2016
Автор метода	Combination: Long et al. (FCN) + Selvaraju et al. (Grad-CAM); formalized as a unified paradigm ~2019–2021	Marco Ribeiro, Sameer Singh & Carlos Guestrin
Тип	Explainable deep learning pipeline	post-hoc local explanation
Основополагающий источник	Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 618–626.	Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?": Explaining the predictions of any classifier. ACM SIGKDD, 1135–1144.
Другие названия	XSS, interpretable semantic segmentation, explainable scene parsing, transparent pixel-wise classification	Local Surrogate Explanations, Model-Agnostic Local Explanations, Locally Faithful Approximations, Yerel Yorumlanabilir Model-Bağımsız Açıklamalar
Связанные	4	2
Сводка	Explainable Semantic Segmentation (XSS) couples pixel-wise scene parsing — assigning a class label to every pixel in an image — with post-hoc or intrinsic explanation methods such as Grad-CAM, attention maps, or SHAP, so that the network's class decisions can be audited, visualized, and justified to domain experts in medical imaging, autonomous driving, and remote sensing.	LIME, introduced by Ribeiro, Singh, and Guestrin in 2016, explains the predictions of any black-box classifier or regressor by building a simple, locally faithful surrogate model around a single prediction of interest. Rather than explaining the global model, LIME focuses on why a specific instance was classified the way it was, making complex models such as deep neural networks and ensemble methods interpretable to end-users, domain experts, and auditors.