LWGANet: Addressing Spatial and Channel Redundancy in Remote Sensing Visual Tasks with Light-Weight Grouped Attention

• URL: http://arxiv.org/abs/2501.10040v2
• Date: Sun, 09 Nov 2025 15:44:23 GMT
• Title: LWGANet: Addressing Spatial and Channel Redundancy in Remote Sensing Visual Tasks with Light-Weight Grouped Attention
• Abstract summary: Light-weight neural networks for remote sensing (RS) visual analysis must overcome two inherent redundancies.<n>Existing models, often designed for natural images, fail to address this dual challenge in RS scenarios.<n>We propose LWGANet, a light-weight backbone engineered for RS-specific properties.
• Score: 13.76497295033739
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Light-weight neural networks for remote sensing (RS) visual analysis must overcome two inherent redundancies: spatial redundancy from vast, homogeneous backgrounds, and channel redundancy, where extreme scale variations render a single feature space inefficient. Existing models, often designed for natural images, fail to address this dual challenge in RS scenarios. To bridge this gap, we propose LWGANet, a light-weight backbone engineered for RS-specific properties. LWGANet introduces two core innovations: a Top-K Global Feature Interaction (TGFI) module that mitigates spatial redundancy by focusing computation on salient regions, and a Light-Weight Grouped Attention (LWGA) module that resolves channel redundancy by partitioning channels into specialized, scale-specific pathways. By synergistically resolving these core inefficiencies, LWGANet achieves a superior trade-off between feature representation quality and computational cost. Extensive experiments on twelve diverse datasets across four major RS tasks--scene classification, oriented object detection, semantic segmentation, and change detection--demonstrate that LWGANet consistently outperforms state-of-the-art light-weight backbones in both accuracy and efficiency. Our work establishes a new, robust baseline for efficient visual analysis in RS images.

Related papers

• DPSF-Net: A Dual-Prior Spatial-Frequency Network for Real-World Remote Sensing Image Dehazing [1.0096416727161845]
  We propose DPSF-Net, a dual-prior spatial-frequency network built on MCAF-Net for real-world RSID.<n>The network uses hazy RGB images and dark channel prior (DCP) maps as joint inputs, allowing physical degradation cues to guide end-to-end feature learning.<n>Experiments demonstrate that DPSF-Net achieves state-of-the-art performance on the real-world RRSHID remote sensing image dehazing benchmark.
  arXiv  Detail & Related papers  (2026-09-07T03:00:10Z)
• Spectral Dynamic Attention Network for Hyperspectral Image Super-Resolution [45.72534786125302]
  Spectral Dynamic Attention Network (SDANet) is a framework designed to adaptively suppress redundant spectral interactions.<n>It achieves state-of-the-art HISR performance while maintaining competitive efficiency.
  arXiv  Detail & Related papers  (2026-04-30T02:13:33Z)
• LRD-Net: A Lightweight Real-Centered Detection Network for Cross-Domain Face Forgery Detection [5.455290019410609]
  We propose LRD-Net (Lightweight Real-centered Detection Network), a novel framework that addresses both challenges simultaneously.<n> LRD-Net adopts a sequential frequency-guided architecture where a lightweight Multi-Scale Wavelet Guidance Module generates attention signals that condition a MobileNetV3-based spatial backbone.<n>Experiments on the DiFF benchmark demonstrate that LRD-Net achieves state-of-the-art cross-domain detection accuracy, consistently outperforming existing methods.
  arXiv  Detail & Related papers  (2026-04-13T00:04:31Z)
• ReGLA: Efficient Receptive-Field Modeling with Gated Linear Attention Network [14.912003445763688]
  textbfReGLA integrates efficient convolutions for local feature extraction with ReLU-based gated linear attention for global modeling.<n>ReGLA outperforms similarly scaled iFormer models in downstream tasks, achieving gains of textbf3.1% AP on object detection and textbf3.6% mIoU on ADE20K semantic segmentation.
  arXiv  Detail & Related papers  (2026-02-05T03:43:29Z)
• GCRPNet: Graph-Enhanced Contextual and Regional Perception Network for Salient Object Detection in Optical Remote Sensing Images [68.33481681452675]
  We propose a graph-enhanced contextual and regional perception network (GCRPNet)<n>It builds upon the Mamba architecture to simultaneously capture long-range dependencies and enhance regional feature representation.<n>It performs adaptive patch scanning on feature maps processed via multi-scale convolutions, thereby capturing rich local region information.
  arXiv  Detail & Related papers  (2025-08-14T11:31:43Z)
• SWAN: Synergistic Wavelet-Attention Network for Infrared Small Target Detection [8.098063209250684]
  Infrared small target detection (IRSTD) is critical in both civilian and military applications.<n>Recent methods focus on conventional convolution operations, which primarily capture local spatial patterns.<n>We propose the Synergistic Wavelet-Attention Network (SWAN), a novel framework designed to perceive targets from both spatial and frequency domains.
  arXiv  Detail & Related papers  (2025-08-02T11:26:58Z)
• RS-TinyNet: Stage-wise Feature Fusion Network for Detecting Tiny Objects in Remote Sensing Images [3.305346506291318]
  We introduce RS-TinyNet, a multi-stage feature fusion and enhancement model specifically tailored for tiny object detection in various RS scenarios.<n> RS-TinyNet comes with two novel designs: tiny object saliency modeling and feature integrity reconstruction.<n>Our experiments show that RS-TinyNet surpasses existing state-of-the-art (SOTA) detectors by 4.0% AP and 6.5% AP75.
  arXiv  Detail & Related papers  (2025-07-17T13:34:21Z)
• A Large-Scale Referring Remote Sensing Image Segmentation Dataset and Benchmark [8.707197692292292]
  We introduce NWPU-Refer, the largest and most diverse RRSIS dataset to date, comprising 15,003 high-resolution images (1024-2048px) spanning 30+ countries with 49,745 annotated targets.<n>We also propose the Multi-scale Referring Network (MRSNet), a novel framework tailored for the unique demands of RRSIS.
  arXiv  Detail & Related papers  (2025-06-04T05:26:51Z)
• AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection [58.67129770371016]
  We propose a novel IRSTD framework that reimagines the IRSTD paradigm by incorporating textual metadata for scene-aware optimization.<n>AuxDet consistently outperforms state-of-the-art methods, validating the critical role of auxiliary information in improving robustness and accuracy.
  arXiv  Detail & Related papers  (2025-05-21T07:02:05Z)
• LSNet: See Large, Focus Small [67.05569159984691]
  We introduce LS (textbfLarge-textbfSmall) convolution, which combines large- kernel perception and small- kernel aggregation. LSNet achieves superior performance and efficiency over existing lightweight networks in various vision tasks.
  arXiv  Detail & Related papers  (2025-03-29T16:00:54Z)
• Semantic-Guided Global-Local Collaborative Networks for Lightweight Image Super-Resolution [9.666827340439669]
  Single-Image Super-Resolution (SISR) plays a pivotal role in enhancing the accuracy and reliability of measurement systems. We propose a Semantic-Guided Global-Local Collaborative Network (SGGLC-Net) for lightweight SISR.
  arXiv  Detail & Related papers  (2025-03-20T11:43:55Z)
• UrbanSAM: Learning Invariance-Inspired Adapters for Segment Anything Models in Urban Construction [51.54946346023673]
  Urban morphology is inherently complex, with irregular objects of diverse shapes and varying scales. The Segment Anything Model (SAM) has shown significant potential in segmenting complex scenes. We propose UrbanSAM, a customized version of SAM specifically designed to analyze complex urban environments.
  arXiv  Detail & Related papers  (2025-02-21T04:25:19Z)
• Renormalized Connection for Scale-preferred Object Detection in Satellite Imagery [51.83786195178233]
  We design a Knowledge Discovery Network (KDN) to implement the renormalization group theory in terms of efficient feature extraction. Renormalized connection (RC) on the KDN enables synergistic focusing'' of multi-scale features. RCs extend the multi-level feature's divide-and-conquer'' mechanism of the FPN-based detectors to a wide range of scale-preferred tasks.
  arXiv  Detail & Related papers  (2024-09-09T13:56:22Z)
• ELGC-Net: Efficient Local-Global Context Aggregation for Remote Sensing Change Detection [65.59969454655996]
  We propose an efficient change detection framework, ELGC-Net, which leverages rich contextual information to precisely estimate change regions. Our proposed ELGC-Net sets a new state-of-the-art performance in remote sensing change detection benchmarks. We also introduce ELGC-Net-LW, a lighter variant with significantly reduced computational complexity, suitable for resource-constrained settings.
  arXiv  Detail & Related papers  (2024-03-26T17:46:25Z)
• Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation [63.15257949821558]
  Referring Remote Sensing Image (RRSIS) is a new challenge that combines computer vision and natural language processing. Traditional Referring Image (RIS) approaches have been impeded by the complex spatial scales and orientations found in aerial imagery. We introduce the Rotated Multi-Scale Interaction Network (RMSIN), an innovative approach designed for the unique demands of RRSIS.
  arXiv  Detail & Related papers  (2023-12-19T08:14:14Z)
• ESDMR-Net: A Lightweight Network With Expand-Squeeze and Dual Multiscale Residual Connections for Medical Image Segmentation [7.921517156237902]
  This paper presents an expand-squeeze dual multiscale residual network ( ESDMR-Net) It is a fully convolutional network that is well-suited for resource-constrained computing hardware such as mobile devices. We present experiments on seven datasets from five distinct examples of applications.
  arXiv  Detail & Related papers  (2023-12-17T02:15:49Z)
• Hi-ResNet: Edge Detail Enhancement for High-Resolution Remote Sensing Segmentation [10.919956120261539]
  High-resolution remote sensing (HRS) semantic segmentation extracts key objects from high-resolution coverage areas. objects of the same category within HRS images show significant differences in scale and shape across diverse geographical environments. We propose a High-resolution remote sensing network (Hi-ResNet) with efficient network structure designs.
  arXiv  Detail & Related papers  (2023-05-22T03:58:25Z)
• Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images [28.560068780733342]
  A novel context aggregation network (CATNet) is proposed to improve the feature extraction process. The proposed model exploits three lightweight plug-and-play modules, namely dense feature pyramid network (DenseFPN), spatial context pyramid ( SCP), and hierarchical region of interest extractor (HRoIE)
  arXiv  Detail & Related papers  (2021-11-22T08:55:25Z)
• RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images [82.1679766706423]
  Salient object detection (SOD) for optical remote sensing images (RSIs) aims at locating and extracting visually distinctive objects/regions from the optical RSIs. We propose a relational reasoning network with parallel multi-scale attention for SOD in optical RSIs. Our proposed RRNet outperforms the existing state-of-the-art SOD competitors both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2021-10-27T07:18:32Z)
• MPRNet: Multi-Path Residual Network for Lightweight Image Super Resolution [2.3576437999036473]
  A novel lightweight super resolution network is proposed, which improves the SOTA performance in lightweight SR. The proposed architecture also contains a new attention mechanism, Two-Fold Attention Module, to maximize the representation ability of the model.
  arXiv  Detail & Related papers  (2020-11-09T17:11:15Z)
• Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution [79.97180849505294]
  We propose a novel coupled unmixing network with a cross-attention mechanism, CUCaNet, to enhance the spatial resolution of HSI. Experiments are conducted on three widely-used HS-MS datasets in comparison with state-of-the-art HSI-SR models.
  arXiv  Detail & Related papers  (2020-07-10T08:08:20Z)
• Object Tracking through Residual and Dense LSTMs [67.98948222599849]
  Deep learning-based trackers based on LSTMs (Long Short-Term Memory) recurrent neural networks have emerged as a powerful alternative. DenseLSTMs outperform Residual and regular LSTM, and offer a higher resilience to nuisances. Our case study supports the adoption of residual-based RNNs for enhancing the robustness of other trackers.
  arXiv  Detail & Related papers  (2020-06-22T08:20:17Z)
• AdaptiveWeighted Attention Network with Camera Spectral Sensitivity Prior for Spectral Reconstruction from RGB Images [22.26917280683572]
  We propose a novel adaptive weighted attention network (AWAN) for spectral reconstruction. AWCA and PSNL modules are developed to reallocate channel-wise feature responses. In the NTIRE 2020 Spectral Reconstruction Challenge, our entries obtain the 1st ranking on the Clean track and the 3rd place on the Real World track.
  arXiv  Detail & Related papers  (2020-05-19T09:21:01Z)
• Learning Enriched Features for Real Image Restoration and Enhancement [166.17296369600774]
  convolutional neural networks (CNNs) have achieved dramatic improvements over conventional approaches for image restoration task. We present a novel architecture with the collective goals of maintaining spatially-precise high-resolution representations through the entire network. Our approach learns an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details.
  arXiv  Detail & Related papers  (2020-03-15T11:04:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.