方法对比

	半监督语义分割	自监督语义分割
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2018–2020	2020–2022
提出者	Multiple (Ouali et al., Zou et al., Chen et al.)	Multiple groups (Caron et al.; Hamilton et al. among key contributors)
类型	Semi-supervised deep learning for pixel-level classification	Self-supervised dense prediction
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.	Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging Properties in Self-Supervised Vision Transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 9650–9660.
别名	Semi-SSL segmentation, pseudo-label segmentation, consistency regularization segmentation, label-efficient semantic segmentation	SSL semantic segmentation, unsupervised semantic segmentation, label-free semantic segmentation, self-supervised dense prediction
相关	5	5
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.	Self-supervised semantic segmentation learns to assign a class label to every pixel of an image without relying on manually annotated segmentation masks. A backbone network is first trained on large quantities of unlabeled images using self-supervised objectives such as contrastive learning or masked image modeling, and the resulting dense features are then used to partition and label image regions, achieving competitive segmentation quality at a fraction of the annotation cost.