IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society最新文献_第3页

Exploiting Joint Representation via Mixture of Experts for Pansharpening 利用混合专家的联合代表进行泛锐化

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-04-27 DOI: 10.1109/LGRS.2026.3687447

Chuang Liu;Mi Wang

{"title":"Exploiting Joint Representation via Mixture of Experts for Pansharpening","authors":"Chuang Liu;Mi Wang","doi":"10.1109/LGRS.2026.3687447","DOIUrl":"https://doi.org/10.1109/LGRS.2026.3687447","url":null,"abstract":"Pansharpening, which aims to reconstruct high-resolution multispectral images (MSIs) by combining low-resolution multispectral observations with high-resolution panchromatic images (PAN), is crucial for overcoming satellite bandwidth limitations. However, existing pansharpening methods typically adopt one of two strategies: 1) employing dual-branch or multibranch architectures with separate feature extraction pipelines for each remote sensing image, which limits their ability to fully exploit synergistic potential; or 2) utilizing a single-branch or shared module approach, which hinders the capture of diverse, source-specific representations. To address these limitations, we propose a novel pansharpening method denoted JRMoE, which incorporates a mixture-of-experts (MoE) framework. JRMoE includes a router that dynamically selects a combination of experts for each input sample, enabling the model to capture both unique and complementary information from different sources. Furthermore, to ensure balanced expert utilization and preserve functional diversity, we introduce a complementarity enhancer and a uniqueness amplifier. The complementarity enhancer prevents overreliance on specific experts, while the uniqueness amplifier encourages individual experts to specialize in distinct aspects of the data, thereby promoting the preservation of distinctive characteristics in the learned representations. Extensive experiments on GF-2, QB, and WV-III benchmarks show that JRMoE consistently outperforms recent pansharpening methods, yielding average gains of 3.77%, 2.96%, and 0.54% in ERGAS, SAM, and Q2n, respectively, over the strongest competing methods on the three test sets. All implementations of this project are released at <uri>https://github.com/JUSTM0VE0N/RSMIF_Project</uri>","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"5002005-5002005"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148488691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hybrid Integration of CNN and Kolmogorov–Arnold Networks for Multispectral Image Super-Resolution 基于CNN和Kolmogorov-Arnold网络的多光谱图像超分辨率混合集成

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-01-12 DOI: 10.1109/LGRS.2026.3652301

Siyuan Zhao;Meihua Bi;Yuxi Wang;Xuyang Teng;Zixuan Guo;Kun Chen;Jie Luo;Kairen Xu;Miao Hu

引用次数: 0

Detecting Ships With SAR Imagery Using Spatiotemporal Fusion: A Case Study of the ESA Sentinel-1 Mission 基于时空融合的SAR图像舰船探测：以ESA Sentinel-1任务为例

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2025-12-18 DOI: 10.1109/LGRS.2025.3646037

Chaoyue Liu;Zongsen Lv;Litao Kang;Zhimin Zhang;Huaitao Fan

引用次数: 0

A Robust RFI Mitigation Method for SAIR Using a Multiscale Dilated and Detail Enhancement Network 基于多尺度扩展和细节增强网络的SAIR鲁棒RFI缓解方法

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2025-11-28 DOI: 10.1109/LGRS.2025.3638605

Jianfei Chen;Ziang Zheng;Fuxin Cai;Gengkun Fang;Leilei Liu

{"title":"A Robust RFI Mitigation Method for SAIR Using a Multiscale Dilated and Detail Enhancement Network","authors":"Jianfei Chen;Ziang Zheng;Fuxin Cai;Gengkun Fang;Leilei Liu","doi":"10.1109/LGRS.2025.3638605","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3638605","url":null,"abstract":"Radio frequency interference (RFI) in the L-band remains a challenge for synthetic aperture interferometric radiometers (SAIRs), degrading data quality and brightness temperature (BT) retrieval accuracy. To address this issue, we propose the multiscale dilated and detail enhancement network (MDDEN), a deep learning (DL)-based method that directly suppresses RFI in the BT domain without requiring auxiliary prior knowledge. MDDEN integrates a multidilated module (MDM) to capture spatially complex interference patterns and a detail enhancement module (DEM) to recover high-frequency BT information. Furthermore, we propose the cross correlation reconstruction error (CCRE), a no-reference metric designed to evaluate RFI mitigation performance. Experiments on both simulated and observed soil moisture and ocean salinity (SMOS) data demonstrate that MDDEN achieves robust and generalizable mitigation across diverse scenarios, delivering high-fidelity BT reconstructions and offering a practical solution for SAIR data processing under RFI contamination.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148489443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SCG-YOLO: Shift-Context Network With Multidirectional Upsampling and Geometric Quality for Small-Object Detection 基于多方向上采样和几何质量的小目标检测偏移上下文网络

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-01-23 DOI: 10.1109/LGRS.2026.3657206

Wei Fan;Yiwen Liu;Xuelong Wang;Huijie He

{"title":"SCG-YOLO: Shift-Context Network With Multidirectional Upsampling and Geometric Quality for Small-Object Detection","authors":"Wei Fan;Yiwen Liu;Xuelong Wang;Huijie He","doi":"10.1109/LGRS.2026.3657206","DOIUrl":"https://doi.org/10.1109/LGRS.2026.3657206","url":null,"abstract":"With the ongoing progress in remote sensing object detection, small-object detection in complex environments still faces difficulties. The representation of small-object features is often limited, and the localization accuracy can be insufficient, which continues to constrain further improvements in overall performance. To address these challenges, we introduce SCG-YOLO, an improved framework based on YOLO11. First, a multidirectional shift channel upsampling (MSCU) module applies a shift channel mix mechanism. By performing directional cyclic shifts and reorganizing features across grouped channels, MSCU recovers high-frequency spatial details lost in downsampling. Second, the C3K2-structured context-guided block (C3K2-CGB) is built by replacing the bottleneck in the backbone’s C3K2 block with a context-guided block (CGB). Using a dual-branch design to capture local details and broader context separately, followed by global refinement, CGB enhances small-object representation in complex backgrounds. Finally, the swish-gated linear unit (SwiGLU)-based localization quality module is integrated into the detection head, where its more stable gradient behavior and more effective feature gating help improve the reliability of bounding box quality assessment for small objects, thereby supporting more accurate localization. On the NWPU-10 and SIMD datasets, SCG-YOLO achieves mAP@0.5 of 85.5% and 82.3%, representing gains of 3.2 and 1.6 percentage points over the baseline.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148489490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fuzzy-Aware Multiview Aggregation Network for Sea–Land Segmentation of Remote Sensing Images 遥感影像海陆分割的模糊感知多视点聚合网络

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-03-12 DOI: 10.1109/LGRS.2026.3673204

Jiantao Peng;Jindong Xu;Jianchao Cui;Haoshi Cui;Haihua Xing

{"title":"Fuzzy-Aware Multiview Aggregation Network for Sea–Land Segmentation of Remote Sensing Images","authors":"Jiantao Peng;Jindong Xu;Jianchao Cui;Haoshi Cui;Haihua Xing","doi":"10.1109/LGRS.2026.3673204","DOIUrl":"https://doi.org/10.1109/LGRS.2026.3673204","url":null,"abstract":"Accurate sea–land segmentation (SLS) of remote sensing images is crucial for monitoring coastline dynamics, which is vital to coastal regions. In remote sensing images, due to the ambiguity of the sea–land boundary, the complexity of the scene, and object scale variation, precise SLS faces significant challenges. In response to the above challenges, we propose a fuzzy-aware multiview aggregation network (FMANet) for accurate SLS of remote sensing images. Specifically, FMANet divides the input image into a global view and a local view, and integrates their features into a single data stream. A multiview feature aggregation module (MFAM) is presented to establish long-distance and deep-level visual interactions among multiple views. A fuzzy-aware module (FAM) is proposed to perceive and refine category boundaries by establishing fuzzy relationships between adjacent pixels and effectively modeling the fuzzy regions of the sea–land boundary. The coarse–fine feature fusion module (CFFM) is put forward to alleviate the misalignment issue of adjacent local views by fusing the coarse segmentation results in the final prediction stage. Comprehensive experimental results on three benchmark SLS datasets show that the proposed FMANet outperforms existing leading methods, confirming its superiority. Additionally, the ablation experiments further verify the effectiveness of each proposed module.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148489567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dual-Domain Flexible Transformer for Pansharpening 双域柔性磨盘变压器

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-03-06 DOI: 10.1109/LGRS.2026.3690952

Qize Yang;Tao Hu;Ke Cao;Liu Liu;Jie Zhang

{"title":"Dual-Domain Flexible Transformer for Pansharpening","authors":"Qize Yang;Tao Hu;Ke Cao;Liu Liu;Jie Zhang","doi":"10.1109/LGRS.2026.3690952","DOIUrl":"https://doi.org/10.1109/LGRS.2026.3690952","url":null,"abstract":"Pansharpening, a crucial task in remote sensing, involves generating high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) and high-resolution panchromatic (PAN) images. Although recent Transformer-based methods improve global context modeling, they suffer from spatially invariant attention windows and neglect the joint modeling of spatial and frequency domains. To overcome these limitations, we propose a novel dual-domain flexible Transformer (DDFformer) that treats pansharpening as a multidomain problem. In particular, we introduce a spatial–frequency flexible attention (SFFA) module that adapts attention windows to scene geometry while preserving high-frequency details through a parallel Haar wavelet transform pathway. Furthermore, we design a dual-domain feature alignment block (FAB) that aligns features from PAN and MS modalities in both spatial and frequency domains via spatial attention and fast Fourier transform (FFT)-based pathways. This dual-path strategy enables more precise feature reconciliation before fusion. Extensive experiments on WorldView-II, GaoFen-2, and WorldView-III datasets show that DDFformer achieves state-of-the-art performance in pansharpening.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"5002205-5002205"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148490051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AFCE-Net: An Adaptive Fusion and Cross-Scale Edge-Aware Network for Remote Sensing Change Detection 面向遥感变化检测的自适应融合跨尺度边缘感知网络

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-06-18 DOI: 10.1109/LGRS.2026.3705161

Rui Huang;Hanfu Shi;Lu Wang;Yan Xing

{"title":"AFCE-Net: An Adaptive Fusion and Cross-Scale Edge-Aware Network for Remote Sensing Change Detection","authors":"Rui Huang;Hanfu Shi;Lu Wang;Yan Xing","doi":"10.1109/LGRS.2026.3705161","DOIUrl":"https://doi.org/10.1109/LGRS.2026.3705161","url":null,"abstract":"Remote sensing change detection (RSCD) still confronts several challenges, particularly pseudo-change interference and blurred object boundaries in complex scenes. These difficulties are often exacerbated by insufficient cross-scale interaction and inadequate boundary refinement in existing methods. We propose an adaptive fusion and cross-scale edge-aware network (AFCE-Net) for accurate RSCD. To bridge the semantic gap and mitigate spatial misalignment caused by hierarchical feature extraction, we propose an adjacent feature enhancement module (AFEM) to strengthen cross-scale contextual aggregation. Furthermore, we design an adaptive weight feature fusion module (AWFFM) to achieve difference-aware feature fusion by combining subtraction, concatenation, and structural similarity (SSIM), yielding more discriminative change-sensitive features. To progressively aggregate global context and refine the details of object boundaries, we develop a cascaded refinement pipeline composed of a cross-scale gated aggregation module (CSGAM) and an edge enhancement attention module (EEAM). We have conducted extensive experiments on three benchmark datasets. The experimental results demonstrate the superiority of our proposed method over SOTA change detectors. The code can be found at <uri>https://github.com/Camille192/AFCENet</uri>","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"7505005-7505005"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148490531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Road Extraction via the Complementary Relationship Between Architectural and Nonarchitectural Areas 基于建筑与非建筑区域互补关系的道路提取

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2025-10-31 DOI: 10.1109/LGRS.2025.3627229

Mingyi Yu;Jie He;Yuan Shen;Cun Ji;Lei Lyu

引用次数: 0

DEM: Dendritic Learning-Incorporated Enhanced 3-D Mamba for Hyperspectral Image Classification DEM：基于树突学习的增强三维曼巴高光谱图像分类

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-03-30 DOI: 10.1109/LGRS.2026.3678883

Shuaibing Shi;Min Li;Yujie He;Wenjing Wang

引用次数: 0