방법 비교

	준지도 학습 의미론적 분할	픽셀 단위의 수동 주석 마스크에 의존하지 않고 이미지의 모든 픽셀에 클래스 레이블을 할당하도록 학습하는 자기 지도 의미론적 분할.
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	2018–2020	2020–2022
창시자	Multiple (Ouali et al., Zou et al., Chen et al.)	Multiple groups (Caron et al.; Hamilton et al. among key contributors)
유형	Semi-supervised deep learning for pixel-level classification	Self-supervised dense prediction
원전	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.
별칭	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
관련	5	5
요약	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.