Módszerek összehasonlítása

	Félfelügyelt példány szegmentálás	Gyengén felügyelt példány-szegmentálás
Tudományterület	Mélytanulás	Mélytanulás
Módszercsalád	Machine learning	Machine learning
Keletkezés éve	2018–2021	2015–2019
Megalkotó	Multiple independent research groups (2018–2021)	Multiple contributors (e.g., Hsu et al., Khoreva et al.)
Típus	Semi-supervised deep learning for dense prediction	Weakly supervised deep learning for pixel-wise instance delineation
Alapmű	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.
Alternatív nevek	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
Kapcsolódó	6	6
Összefoglaló	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.