Сравнение методов

	Полуавтоматическая сегментация экземпляров	Слабо контролируемая сегментация экземпляров
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2018–2021	2015–2019
Автор метода	Multiple independent research groups (2018–2021)	Multiple contributors (e.g., Hsu et al., Khoreva et al.)
Тип	Semi-supervised deep learning for dense prediction	Weakly supervised deep learning for pixel-wise instance delineation
Основополагающий источник	Hu, H., Wei, P., Zheng, H., Bai, X., Wei, Y., & Chen, Y. (2021). Semi-supervised Semantic Segmentation via Adaptive Equalization Learning. Advances in Neural Information Processing Systems (NeurIPS), 34, 22106–22118.	Hsu, C.-C., Hsu, K.-J., Tsai, C.-C., Lin, Y.-Y., & Chuang, Y.-Y. (2019). Weakly supervised instance segmentation using the bounding box tightness prior. Advances in Neural Information Processing Systems (NeurIPS), 32.
Другие названия	Semi-supervised Mask R-CNN, pseudo-label instance segmentation, label-efficient instance segmentation, SSIS	WSIS, weakly-supervised mask prediction, weak-label instance segmentation, box-supervised instance segmentation
Связанные	6	6
Сводка	Semi-supervised instance segmentation trains a model to detect and delineate every object instance in an image using a small labeled set and a large unlabeled image corpus. By generating pseudo-labels from confident predictions on unlabeled images and enforcing consistency under augmentation, the approach achieves competitive mask accuracy at a fraction of the full annotation cost.	Weakly supervised instance segmentation trains deep networks to delineate individual object instances at pixel level using only cheap, incomplete annotations — such as bounding boxes, image-level labels, or point clicks — rather than costly full pixel-wise masks. It dramatically reduces annotation effort while still producing instance-level masks for each object in an image.