Salīdzināt metodes

	Pusuzraudzīta instanču segmentācija	Daļēji uzraudzīts konvolucionāls neironu tīkls
Nozare	Dziļā mācīšanās	Dziļā mācīšanās
Saime	Machine learning	Machine learning
Izcelsmes gads	2018–2021	2013–2017
Autors	Multiple independent research groups (2018–2021)	Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others)
Tips	Semi-supervised deep learning for dense prediction	Semi-supervised deep learning
Pirmavots	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.
Citi nosaukumi	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
Saistītās	6	5
Kopsavilkums	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.