CARE: Confidence-Aware Regression Estimation of building density fine-tuning EO Foundation Models
This addresses the problem of unreliable predictions in Earth Observation applications for remote sensing practitioners, though it appears incremental as it builds on existing foundation model approaches.
The researchers tackled the challenge of confidence quantification in pixel-wise regression tasks for Earth Observation Foundation Models by developing the CARE model, which assigns confidence metrics to regression outputs and uses a self-corrective learning method for low-confidence regions, showing it outperforms baseline methods on Sentinel-2 satellite data for building density estimation.
Performing accurate confidence quantification and assessment in pixel-wise regression tasks, which are downstream applications of AI Foundation Models for Earth Observation (EO), is important for deep neural networks to predict their failures, improve their performance and enhance their capabilities in real-world applications, for their practical deployment. For pixel-wise regression tasks, specifically utilizing remote sensing data from satellite imagery in EO Foundation Models, confidence quantification is a critical challenge. The focus of this research work is on developing a Foundation Model using EO satellite data that computes and assigns a confidence metric alongside regression outputs to improve the reliability and interpretability of predictions generated by deep neural networks. To this end, we develop, train and evaluate the proposed Confidence-Aware Regression Estimation (CARE) Foundation Model. Our model CARE computes and assigns confidence to regression results as downstream tasks of a Foundation Model for EO data, and performs a confidence-aware self-corrective learning method for the low-confidence regions. We evaluate the model CARE, and experimental results on multi-spectral data from the Copernicus Sentinel-2 satellite constellation to estimate the building density (i.e. monitoring urban growth), show that the proposed method can be successfully applied to important regression problems in EO and remote sensing. We also show that our model CARE outperforms other baseline methods.