Position-Aware Differential Denoising Transformer for Semantic Segmentation of Remote Sensing Images

Li X, Shi C, Xu N, Su Y, Kaup A, Liu D, Li X (2025)

Publication Language: English

Publication Type: Journal article

Publication year: 2025

Journal

IEEE Geoscience and Remote Sensing Letters Institute of Electrical and Electronics Engineers (IEEE)

Book Volume: 23

Pages Range: 1-5

DOI: 10.1109/LGRS.2025.3649407

Abstract

Semantic segmentation of high-resolution remote sensing images (HRRSIs) is essential for various geospatial applications. While recent transformer-based models demonstrate promising global modeling capabilities, they are susceptible to attention noise—particularly in cluttered or noisy scenes—leading to degraded segmentation quality. This challenge is amplified in HRRSIs, where spatially heterogeneous noise and ambiguous object boundaries are prevalent. To address this problem, we propose PDDFormer, a Position-aware Differential Denoising Transformer tailored for semantic segmentation of HRRSIs. Central to our design is the Spatially Gated Differential Attention (SGDA), which adaptively modulates denoising strength across spatial positions using a learnable gate. Unlike prior differential attention models, SGDA introduces position-aware denoising that dynamically adjusts attention suppression at each token, guided by spatial semantics. This allows PDDFormer to suppress redundant background responses while preserving critical structural semantics. Extensive experiments on two public benchmarks, ISPRS Potsdam and LoveDA, demonstrate that PDDFormer consistently outperforms state-of-the-art methods in both accuracy and boundary preservation. Moreover, PDDFormer achieves favorable performance-efficiency trade-offs, making it practical for large-scale geospatial analysis. Visualizations further confirm the model’s ability to generate cleaner, more coherent segmentation maps, validating the effectiveness of our spatially adaptive denoising strategy.

Involved external institutions

Hohai University CN China (CN) Shenzhen University (SZU) / 深圳大学 CN China (CN) Yellow River Conservancy Technical University / 黃河水利技術大學 CN China (CN) University of Macau (UM) / Universidade de Macau / 澳門大學 MO Macao (MO)

How to cite

APA:

Li, X., Shi, C., Xu, N., Su, Y., Kaup, A., Liu, D., & Li, X. (2026). Position-Aware Differential Denoising Transformer for Semantic Segmentation of Remote Sensing Images. IEEE Geoscience and Remote Sensing Letters, 23, 1-5. https://doi.org/10.1109/LGRS.2025.3649407

MLA:

Li, Xin, et al. "Position-Aware Differential Denoising Transformer for Semantic Segmentation of Remote Sensing Images." IEEE Geoscience and Remote Sensing Letters 23 (2026): 1-5.

BibTeX: Download