Machine learningDeep learning / NLP / CV
半监督语义分割
半监督语义分割使用少量全标注图像结合大量无标注图像来训练像素级标注模型。伪标签和一致性正则化等技术从无标注数据中提取监督信号，从而能够以较低的标注成本达到接近全监督的精度。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- 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. DOI: 10.1109/CVPR42600.2020.01269 ↗
- Zou, Y., Zhang, Z., Zhang, H., Li, C.-L., Bian, X., Huang, J.-B., & Pfister, T. (2020). PseudoSeg: Designing Pseudo Labels for Semantic Segmentation. International Conference on Learning Representations (ICLR 2021). link ↗
如何引用本页
ScholarGate. (2026, June 3). Semi-supervised Semantic Segmentation (Pseudo-label and Consistency-based). ScholarGate. https://scholargate.app/zh/deep-learning/semi-supervised-semantic-segmentation
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →