Semi-Supervised Learning for hyperspectral images by non parametrically predicting view assignment
This addresses the problem of high-dimensional data requiring large labeled sets for researchers in remote sensing, but it appears incremental as it builds on existing semi-supervised and self-supervised techniques.
The paper tackles hyperspectral image classification with limited labeled data by proposing a semi-supervised method that assigns pseudo-labels from labeled samples to augmented views of unlabeled data, showing improved performance over self-supervised and supervised approaches on Houston and Pavia University datasets.
Hyperspectral image (HSI) classification is gaining a lot of momentum in present time because of high inherent spectral information within the images. However, these images suffer from the problem of curse of dimensionality and usually require a large number samples for tasks such as classification, especially in supervised setting. Recently, to effectively train the deep learning models with minimal labelled samples, the unlabeled samples are also being leveraged in self-supervised and semi-supervised setting. In this work, we leverage the idea of semi-supervised learning to assist the discriminative self-supervised pretraining of the models. The proposed method takes different augmented views of the unlabeled samples as input and assigns them the same pseudo-label corresponding to the labelled sample from the downstream task. We train our model on two HSI datasets, namely Houston dataset (from data fusion contest, 2013) and Pavia university dataset, and show that the proposed approach performs better than self-supervised approach and supervised training.