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	弱教師あり意味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	2014–2016
提唱者	Multiple contributors (e.g., Hsu et al., Khoreva et al.)	Multiple contributors; Class Activation Mapping (Zhou et al., 2016) is foundational
種類	Weakly supervised deep learning for pixel-wise instance delineation	Pixel-level classification with image-level or coarse supervision
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.	Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning Deep Features for Discriminative Localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2921–2929.
別名	WSIS, weakly-supervised mask prediction, weak-label instance segmentation, box-supervised instance segmentation	WSSS, weak-label segmentation, image-level supervised segmentation, weakly-labeled pixel classification
関連	6	4
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.	Weakly Supervised Semantic Segmentation (WSSS) trains pixel-level scene parsers using only cheap, coarse annotations — typically image-level class tags — instead of costly dense pixel masks. By generating proxy pseudo-labels from a classification network (via Class Activation Maps or similar localisation cues) and iteratively refining them, WSSS brings full-supervision accuracy within reach at a fraction of the annotation cost.