Dynamic Class-Aware Active Learning for Unbiased Satellite Image Segmentation

2026-04-10

AI Summary

This work addresses the challenges of high annotation costs and severe class imbalance in satellite image semantic segmentation, where existing active learning methods often exhibit bias against rare or poorly performing classes. To mitigate this issue, the authors propose a Dynamic Class-Aware Uncertainty Active Learning framework (DCAU-AL) that continuously monitors per-class segmentation performance and adaptively adjusts sample selection weights to prioritize underrepresented or currently worst-performing classes. By integrating class-level performance evaluation, dynamic sampling strategies, and uncertainty quantification, DCAU-AL significantly outperforms state-of-the-art active learning approaches on the OpenEarth land cover dataset, achieving higher mean class-wise Intersection over Union (mIoU) and improved labeling efficiency under strong class imbalance.

Technology Category

• Machine Learning: Active Learning
• Computer Vision: Segmentation
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Semantics and Knowledge: Representation, semantic annotation, enhancement, enrichments, access and/or integration of a variety of data on the Web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

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.

Problem

• Active Learning
• Class Imbalance
• Satellite Image Segmentation
• Semantic Segmentation
• Annotation Bias

Innovation

• Active Learning
• Class Imbalance
• Semantic Segmentation
• Dynamic Sampling
• Satellite Imagery