Сравнение методов

	Дообученная семантическая сегментация	Сегментация экземпляров
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2015–2018	2017
Автор метода	Long, Shelhamer & Darrell (FCN); Chen et al. (DeepLab)	He, K., Gkioxari, G., Dollar, P., Girshick, R.
Тип	Transfer learning / dense prediction	Pixel-level detection and mask prediction
Основополагающий источник	Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3431–3440.	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	fine-tuned semseg, domain-adapted semantic segmentation, transfer learning semantic segmentation, pretrained dense prediction fine-tuning	instance-level segmentation, object instance segmentation, mask prediction, panoptic instance segmentation
Связанные	4	4
Сводка	Fine-tuned semantic segmentation adapts a deep neural network pre-trained on a large pixel-labelled dataset (e.g., ImageNet-pretrained backbone with an encoder-decoder head trained on COCO or Cityscapes) to a new target domain by continuing training on domain-specific annotated images. The result is a model that assigns a class label to every pixel in an image while leveraging rich visual representations learned from vastly more data than the target domain alone could provide.	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.