Ladder Networks for Semi-Supervised Hyperspectral Image Classification
This addresses the problem of data scarcity in remote sensing for researchers, but it is incremental as it adapts an existing method to a new domain.
The paper tackled hyperspectral image classification with limited labeled data by applying the Ladder Network in a semi-supervised setting, achieving new state-of-the-art performance on the Pavia University dataset with only 5 labeled points per class.
We used the Ladder Network [Rasmus et al. (2015)] to perform Hyperspectral Image Classification in a semi-supervised setting. The Ladder Network distinguishes itself from other semi-supervised methods by jointly optimizing a supervised and unsupervised cost. In many settings this has proven to be more successful than other semi-supervised techniques, such as pretraining using unlabeled data. We furthermore show that the convolutional Ladder Network outperforms most of the current techniques used in hyperspectral image classification and achieves new state-of-the-art performance on the Pavia University dataset given only 5 labeled data points per class.