Сравнение методов

	Семантическая сегментация с частичной разметкой	Полу-контролируемая свёрточная нейронная сеть
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2018–2020	2013–2017
Автор метода	Multiple (Ouali et al., Zou et al., Chen et al.)	Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others)
Тип	Semi-supervised deep learning for pixel-level classification	Semi-supervised deep learning
Основополагающий источник	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.	Lee, D.-H. (2013). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. ICML Workshop on Challenges in Representation Learning.
Другие названия	Semi-SSL segmentation, pseudo-label segmentation, consistency regularization segmentation, label-efficient semantic segmentation	SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN
Связанные	5	5
Сводка	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.	A Semi-supervised CNN trains a convolutional network on a small labeled image set and a larger pool of unlabeled images simultaneously, using techniques such as pseudo-labeling and consistency regularization to extract supervisory signal from unlabeled data. This strategy closes much of the performance gap caused by scarce annotations without requiring additional human labeling effort.