Uncertainty-Aware Graph Self-Supervised Learning for Hyperspectral Image Change Detection

Deep learning-based hyperspectral image (HSI) change detection (CD) has been a research hotspot. However, the high dimensionality and the limited training samples make HSI-CD difficult to implement. Besides, the data uncertainty inherited from HSIs is often neglected. To deal with these issues, this article presents an uncertainty-aware graph self-supervised learning (UA-GSSL) approach for unsupervised HSI-CD, which allows encoding not only the spectral and topological structure attributes but also the data uncertainty into learned feature representation for downstream CD task. Specifically, spectral and spatial correlations in HSIs are first characterized via graph model. Then, based on the constructed spectral–spatial graph models, novel node- and edge-level data augmentations are devised to enrich the contrastive sample pairs. Third, a graph-based dual-branch self-supervised learning (SSL) contrastive network is designed to maximize the mutual information between a pair of low-dimensional feature embeddings. Fourth, a simple but effective UA loss function is dedicatedly formed to encourage reliable features to play the more dominant role in feature representation. Finally, a change map is produced using the learned features. Experimental results obtained on four real HSI datasets sufficiently demonstrate that the UA-GSSL achieves remarkable results compared to 12 state-of-the-art (SOTA) methods. The source code of this article can be downloaded from
https://github.com/vickyiiiii/UA-GSSL
.