Ladder Networks for Semi-Supervised Hyperspectral Image Classification

TL;DR

This paper demonstrates that convolutional Ladder Networks effectively perform semi-supervised hyperspectral image classification, outperforming existing methods and achieving state-of-the-art results with minimal labeled data.

Contribution

The study introduces the application of convolutional Ladder Networks to hyperspectral image classification, showing superior performance in semi-supervised settings.

Findings

Outperforms most current techniques in hyperspectral classification

Achieves state-of-the-art results on Pavia University dataset

Requires only 5 labeled data points per class

Abstract

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.