手法を比較

	弱教師ありインスタンスセグメンテーション	半教師ありインスタンスセグメンテーション
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2015–2019	2018–2021
提唱者	Multiple contributors (e.g., Hsu et al., Khoreva et al.)	Multiple independent research groups (2018–2021)
種類	Weakly supervised deep learning for pixel-wise instance delineation	Semi-supervised deep learning for dense prediction
原典	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.
別名	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
関連	6	6
概要	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.