Machine learningDeep learning / NLP / CV
半监督目标检测
半监督目标检测（Semi-supervised object detection）是指在少量标注图像和大量未标注图像上训练目标检测器。教师模型为未标注图像生成伪标签，学生模型则同时学习真实标注数据和伪标注数据，这极大地减少了昂贵的手动边界框标注负担，同时实现了与全监督基线模型相当的准确性。
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
- Sohn, K., Zhang, Z., Li, C.-L., Zhang, H., Lee, C.-Y., & Pfister, T. (2020). A Simple Semi-Supervised Learning Framework for Object Detection. arXiv preprint arXiv:2005.04757. link ↗
- Liu, Y.-C., Ma, C.-Y., He, Z., Kuo, C.-W., Chen, K., Zhang, P., Wu, B., Kira, Z., & Vajda, P. (2021). Unbiased Teacher for Semi-Supervised Object Detection. ICLR 2021. link ↗
如何引用本页
ScholarGate. (2026, June 3). Semi-supervised Object Detection (Pseudo-label / Mean-Teacher Paradigm). ScholarGate. https://scholargate.app/zh/deep-learning/semi-supervised-object-detection
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.
- 实例分割深度学习↔ compare
- 目标检测深度学习↔ compare
- 半监督卷积神经网络深度学习↔ compare
- 半监督图像分类深度学习↔ compare
- 基于对象检测的迁移学习深度学习↔ compare
- 弱监督目标检测深度学习↔ compare