Сравнение методов

	Объяснимое сегментирование экземпляров	Сегментация экземпляров
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2017–present	2017
Автор метода	He, K. et al. (Mask R-CNN); XAI extensions by multiple authors	He, K., Gkioxari, G., Dollar, P., Girshick, R.
Тип	Explainability-augmented deep learning pipeline	Pixel-level detection and mask prediction
Основополагающий источник	Lindner, M., Meng, C., & Bischl, B. (2023). Explaining Instance Segmentation Models via Saliency Maps and Occlusion. IEEE Transactions on Pattern Analysis and Machine Intelligence.	He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2961–2969.
Другие названия	XAI instance segmentation, interpretable instance segmentation, transparent mask prediction, explainable Mask R-CNN	instance-level segmentation, object instance segmentation, mask prediction, panoptic instance segmentation
Связанные	6	4
Сводка	Explainable Instance Segmentation combines deep-learning instance segmentation models — which detect and delineate every individual object as a separate pixel mask — with post-hoc or ante-hoc explainability techniques such as GradCAM, SHAP, LIME, or attention visualization, so that each predicted mask is accompanied by evidence showing which image regions drove the model's decision.	Instance segmentation is a computer vision task that simultaneously detects every distinct object in an image and produces a precise pixel-level mask for each individual object instance. Unlike semantic segmentation, which labels every pixel with a class, instance segmentation distinguishes between separate objects of the same class, enabling fine-grained spatial understanding.