Порівняння методів

	Напівкерована семантична сегментація	Сегментація екземплярів
Галузь	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning
Рік появи	2018–2020	2017
Автор методу	Multiple (Ouali et al., Zou et al., Chen et al.)	He, K., Gkioxari, G., Dollar, P., Girshick, R.
Тип	Semi-supervised deep learning for pixel-level classification	Pixel-level detection and mask prediction
Основоположне джерело	Ouali, Y., Hudelot, C., & Tami, M. (2020). Semi-Supervised Semantic Segmentation with Cross-Consistency Training. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12674–12684.	He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2961–2969.
Інші назви	Semi-SSL segmentation, pseudo-label segmentation, consistency regularization segmentation, label-efficient semantic segmentation	instance-level segmentation, object instance segmentation, mask prediction, panoptic instance segmentation
Пов'язані	5	4
Підсумок	Semi-supervised semantic segmentation trains pixel-level labeling models using a small set of fully labeled images combined with a much larger set of unlabeled images. Techniques such as pseudo-labeling and consistency regularization extract supervisory signal from unlabeled data, making it possible to achieve near-fully-supervised accuracy at a fraction of the annotation cost.	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.