Võrdle meetodeid

	Nõrgalt juhendatud üksikobjektide segmentimine	Poolitatud juhuslik segmenteerimine
Valdkond	Süvaõpe	Süvaõpe
Perekond	Machine learning	Machine learning
Tekkeaasta	2015–2019	2018–2021
Looja	Multiple contributors (e.g., Hsu et al., Khoreva et al.)	Multiple independent research groups (2018–2021)
Tüüp	Weakly supervised deep learning for pixel-wise instance delineation	Semi-supervised deep learning for dense prediction
Algallikas	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.
Rööpnimetused	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
Seotud	6	6
Kokkuvõte	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.