方法对比

	半监督语义分割	弱监督语义分割
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2018–2020	2014–2016
提出者	Multiple (Ouali et al., Zou et al., Chen et al.)	Multiple contributors; Class Activation Mapping (Zhou et al., 2016) is foundational
类型	Semi-supervised deep learning for pixel-level classification	Pixel-level classification with image-level or coarse supervision
开创性文献	Ouali, Y., Hudelot, C., & Tami, M. (2020). Semi-Supervised Semantic Segmentation with Cross-Consistency Training. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12674–12684.	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.
别名	Semi-SSL segmentation, pseudo-label segmentation, consistency regularization segmentation, label-efficient semantic segmentation	WSSS, weak-label segmentation, image-level supervised segmentation, weakly-labeled pixel classification
相关	5	4
摘要	Semi-supervised semantic segmentation trains pixel-level labeling models using a small set of fully labeled images combined with a much larger set of unlabeled images. Techniques such as pseudo-labeling and consistency regularization extract supervisory signal from unlabeled data, making it possible to achieve near-fully-supervised accuracy at a fraction of the annotation cost.	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.