Сравнение на методи

	Слабо контролирана сегментация на отделни обекти	Полу-наблюдавано сегментиране на инстанции
Област	Дълбоко обучение	Дълбоко обучение
Семейство	Machine learning	Machine learning
Година на възникване	2015–2019	2018–2021
Създател	Multiple contributors (e.g., Hsu et al., Khoreva et al.)	Multiple independent research groups (2018–2021)
Тип	Weakly supervised deep learning for pixel-wise instance delineation	Semi-supervised deep learning for dense prediction
Основополагащ източник	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.	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.
Други названия	WSIS, weakly-supervised mask prediction, weak-label instance segmentation, box-supervised instance segmentation	Semi-supervised Mask R-CNN, pseudo-label instance segmentation, label-efficient instance segmentation, SSIS
Свързани	6	6
Резюме	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.	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.