Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images
This work addresses the need for efficient semi-supervised learning in remote sensing applications like monitoring deforestation and urbanization, but it is incremental as it applies known active learning methods to a specific domain.
The paper tackled the problem of limited labeled data for semantic segmentation in satellite images by proposing an active learning-based sampling strategy to select a representative labeled set, resulting in a 27% improvement in mIoU with only 2% labeled data compared to random sampling.
Remote sensing data is crucial for applications ranging from monitoring forest fires and deforestation to tracking urbanization. Most of these tasks require dense pixel-level annotations for the model to parse visual information from limited labeled data available for these satellite images. Due to the dearth of high-quality labeled training data in this domain, there is a need to focus on semi-supervised techniques. These techniques generate pseudo-labels from a small set of labeled examples which are used to augment the labeled training set. This makes it necessary to have a highly representative and diverse labeled training set. Therefore, we propose to use an active learning-based sampling strategy to select a highly representative set of labeled training data. We demonstrate our proposed method's effectiveness on two existing semantic segmentation datasets containing satellite images: UC Merced Land Use Classification Dataset and DeepGlobe Land Cover Classification Dataset. We report a 27% improvement in mIoU with as little as 2% labeled data using active learning sampling strategies over randomly sampling the small set of labeled training data.