Active learning and semi-supervised learning are both important techniques to improve the learned model using unlabeled data, when labeled data is difficult to obtain, and unlabeled data is available ...

Source Codes for super resolution of the lunar elemental abundance map using a semi-supervised deep spatial interpolation model. This hybrid approach combined ResNet50 for spatial feature extraction ...

A semi-supervised learning is then used to recognize sub-classes by utilizing very few labeled samples per each sub-class and a large number of unlabeled samples. Experimental results on real remotely ...