Debiased Learning for Remote Sensing Data
This work addresses the annotation scarcity problem for remote sensing data, which is an incremental improvement over existing semi-supervised methods.
The paper tackles the problem of limited labeled data for remote sensing imagery by proposing a semi-supervised learning approach that adapts FixMatch with domain-specific augmentations and debiases imbalanced training data. Using only 30% of labeled annotations, it achieves a 7.1% accuracy gain over the supervised baseline and a 2.1% gain over the state-of-the-art CDS method on the xView dataset.
Deep learning has had remarkable success at analyzing handheld imagery such as consumer photos due to the availability of large-scale human annotations (e.g., ImageNet). However, remote sensing data lacks such extensive annotation and thus potential for supervised learning. To address this, we propose a highly effective semi-supervised approach tailored specifically to remote sensing data. Our approach encompasses two key contributions. First, we adapt the FixMatch framework to remote sensing data by designing robust strong and weak augmentations suitable for this domain. Second, we develop an effective semi-supervised learning method by removing bias in imbalanced training data resulting from both actual labels and pseudo-labels predicted by the model. Our simple semi-supervised framework was validated by extensive experimentation. Using 30\% of labeled annotations, it delivers a 7.1\% accuracy gain over the supervised learning baseline and a 2.1\% gain over the supervised state-of-the-art CDS method on the remote sensing xView dataset.