Dynamic Class-Aware Active Learning for Unbiased Satellite Image Segmentation

TL;DR

This paper introduces DCAU-AL, a novel active learning method that dynamically prioritizes underperforming classes in satellite image segmentation, significantly reducing annotation costs and bias.

Contribution

The paper proposes a class-aware adaptive active learning strategy that adjusts sampling focus based on real-time class performance, improving segmentation accuracy in imbalanced datasets.

Findings

DCAU-AL outperforms existing AL methods on the OpenEarth dataset.

It achieves higher per-class IoU, especially for underrepresented classes.

DCAU-AL reduces annotation effort while maintaining high segmentation quality.

Abstract

Semantic segmentation of satellite imagery plays a vital role in land cover mapping and environmental monitoring. However, annotating large-scale, high-resolution satellite datasets is costly and time consuming, especially when covering vast geographic regions. Instead of randomly labeling data or exhaustively annotating entire datasets, Active Learning (AL) offers an efficient alternative by intelligently selecting the most informative samples for annotation with the help of Human-in-the-loop (HITL), thereby reducing labeling costs while maintaining high model performance. AL is particularly beneficial for large-scale or resource-constrained satellite applications, as it enables high segmentation accuracy with significantly fewer labeled samples. Despite these advantages, standard AL strategies typically rely on global uncertainty or diversity measures and lack the adaptability to target underperforming or rare classes as training progresses, leading to bias in the system. To overcome these limitations, we propose a novel adaptive acquisition function, Dynamic Class-Aware Uncertainty based Active learning (DCAU-AL) that prioritizes sample selection based on real-time class-wise performance gaps, thereby overcoming class-imbalance issue. The proposed DCAU-AL mechanism continuously tracks the performance of the segmentation per class and dynamically adjusts the sampling weights to focus on poorly performing or underrepresented classes throughout the active learning process. Extensive experiments on the OpenEarth land cover dataset show that DCAU-AL significantly outperforms existing AL methods, especially under severe class imbalance, delivering superior per-class IoU and improved annotation efficiency.