Work

DMRS: Long-tailed remote sensing recognition via semantic-aware mixing and diversity experts

Year: 2025

Type: article

Abstract: Long-tailed class distributions pose a significant challenge in remote sensing scene recognition, where certain scene categories appear far less frequently than others. However, existing long-tailed learning approaches often overlook the unique spatial hierarchies and contextual semantic relationships inherent in remote sensing imagery, limiting their effectiveness in this domain. To address this, we propose Diversity-Mix Remote Sensing (DMRS), a foundation model-based framework designed for long-tailed remote sensing scene recognition. DMRS introduces two key innovations: (1) multi-low-rank adaptation diversity experts, which achieves balanced classification by specializing different experts for different regions of the class distribution, and (2) a semantic-aware mixing strategy, which incorporates textual semantic information typically unused in traditional classification to enhance perception across diverse remote sensing scenes. Extensive experiments on NWPU-RESISC45 and RSD46-WHU datasets demonstrate the effectiveness of DMRS, achieving 6.7% and 2.0% improvements in overall accuracy, respectively, while significantly enhancing the recognition of tail classes. These results highlight the potential of DMRS in tackling long-tail challenges in remote sensing scene classification. The data and codes used in the study are detailed in: https://github.com/wyfhbb/DMRS .

Source: International Journal of Applied Earth Observation and Geoinformation

DOI: 10.1016/j.jag.2025.104623

Authors: Yifan Wang, Fan Zhang, Qihao Zhao, Wei Hu, Fei Ma

Institutions: Beijing University of Chemical Technology, Singapore University of Technology and Design

Language: English

Topic: Remote-Sensing Image Classification

Subfield: Media Technology

Field: Engineering

Domain: Physical Sciences

SDG: Reduced inequalities

Open Access status: gold

Estimated APC paid: $3,550