Hierarchical Semi-Supervised Active Learning for Remote Sensing

TL;DR

This paper introduces a Hierarchical Semi-Supervised Active Learning framework for remote sensing that combines SSL and a novel hierarchical active learning strategy to efficiently utilize unlabeled data, significantly reducing labeling costs while maintaining high accuracy.

Contribution

The paper proposes a new hierarchical active learning method integrated with semi-supervised learning for remote sensing, improving sample selection efficiency and model performance with minimal labeled data.

Findings

HSSAL outperforms SSL and AL baselines on benchmark datasets.

Achieves over 95% accuracy with as little as 2-8% labeled data.

Demonstrates high label efficiency and effective utilization of unlabeled data.

Abstract

The performance of deep learning models in remote sensing (RS) strongly depends on the availability of high-quality labeled data. However, collecting large-scale annotations is costly and time-consuming, while vast amounts of unlabeled imagery remain underutilized. To address this challenge, we propose a Hierarchical Semi-Supervised Active Learning (HSSAL) framework that integrates semi-supervised learning (SSL) and a novel hierarchical active learning (HAL) in a closed iterative loop. In each iteration, SSL refines the model using both labeled data through supervised learning and unlabeled data via weak-to-strong self-training, improving feature representation and uncertainty estimation. Guided by the refined representations and uncertainty cues of unlabeled samples, HAL then conducts sample querying through a progressive clustering strategy, selecting the most informative instances that jointly satisfy the criteria of scalability, diversity, and uncertainty. This hierarchical process ensures both efficiency and representativeness in sample selection. Extensive experiments on three benchmark RS scene classification datasets, including UCM, AID, and NWPU-RESISC45, demonstrate that HSSAL consistently outperforms SSL- or AL-only baselines. Remarkably, with only 8%, 4%, and 2% labeled training data on UCM, AID, and NWPU-RESISC45, respectively, HSSAL achieves over 95% of fully-supervised accuracy, highlighting its superior label efficiency through informativeness exploitation of unlabeled data. Our code will be publicly available.