Comparer des méthodes

	Segmentation d'instances semi-supervisée	CNN convolutive semi-supervisée
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2018–2021	2013–2017
Auteur d'origine	Multiple independent research groups (2018–2021)	Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others)
Type	Semi-supervised deep learning for dense prediction	Semi-supervised deep learning
Source fondatrice	Hu, H., Wei, P., Zheng, H., Bai, X., Wei, Y., & Chen, Y. (2021). Semi-supervised Semantic Segmentation via Adaptive Equalization Learning. Advances in Neural Information Processing Systems (NeurIPS), 34, 22106–22118.	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.
Alias	Semi-supervised Mask R-CNN, pseudo-label instance segmentation, label-efficient instance segmentation, SSIS	SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN
Apparentées	6	5
Résumé	Semi-supervised instance segmentation trains a model to detect and delineate every object instance in an image using a small labeled set and a large unlabeled image corpus. By generating pseudo-labels from confident predictions on unlabeled images and enforcing consistency under augmentation, the approach achieves competitive mask accuracy at a fraction of the full 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.