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

arXiv: https://arxiv.org/abs/2501.10040 · HTML: https://mlsanity.com/paper/2501.10040/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 17 Jan 2025.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification](https://mlsanity.com/paper/1608.05167/) (2016)
- [Remote Sensing Image Change Detection with Transformers](https://mlsanity.com/paper/2103.00208/) (2021)
- [A Transformer-Based Siamese Network for Change Detection](https://mlsanity.com/paper/2201.01293/) (2022)
- [Co-Scale Conv-Attentional Image Transformers](https://mlsanity.com/paper/2104.06399/) (2021)
- [ReDet: A Rotation-equivariant Detector for Aerial Object Detection](https://mlsanity.com/paper/2103.07733/) (2021)
- [UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery](https://mlsanity.com/paper/2109.08937/) (2021)
- [Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks](https://mlsanity.com/paper/2303.03667/) (2023)
- [Rethinking Vision Transformers for MobileNet Size and Speed](https://mlsanity.com/paper/2212.08059/) (2022)
- [Anchor-free Oriented Proposal Generator for Object Detection](https://mlsanity.com/paper/2110.01931/) (2021)
- [Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2011.09766/) (2020)
- [Poly Kernel Inception Network for Remote Sensing Detection](https://mlsanity.com/paper/2403.06258/) (2024)

## Built on by (most cited first, 10 of 10)

- [Real-World Remote Sensing Image Dehazing: Benchmark and Baseline](https://mlsanity.com/paper/2503.17966/) (2025)
- [M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detection](https://mlsanity.com/paper/2505.10931/) (2025)
- [LightFormer: A lightweight and efficient decoder for remote sensing image segmentation](https://mlsanity.com/paper/2504.10834/) (2025)
- [FTCFormer: Fuzzy Token Clustering Transformer for Image Classification](https://mlsanity.com/paper/2507.10283/) (2025)
- [Improving Remote Sensing Classification using Topological Data Analysis and Convolutional Neural Networks](https://mlsanity.com/paper/2507.10381/) (2025)
- [RSRWKV: A Linear-Complexity 2D Attention Mechanism for Efficient Remote Sensing Vision Task](https://mlsanity.com/paper/2503.20382/) (2025)
- [SARU: A Shadow-Aware and Removal Unified Framework for Remote Sensing Images with New Benchmarks](https://mlsanity.com/paper/2604.25432/) (2026)
- [ASFR-Net: Adversarial Alignment and Spatio-Frequency Refinement Network for Heterogeneous Remote Sensing Image Change Detection](https://mlsanity.com/paper/2607.07161/) (2026)
- [ProtoRAG: Prototype-Based Retrieval Augmentation for Few-Shot Fine-Grained Remote Sensing Object Detection](https://mlsanity.com/paper/2609.05953/) (2026)
- [SPEANet: Structural Prior Enhanced Attention Network for Parameter-Efficient Remote Sensing Object Detection](https://mlsanity.com/paper/2609.26064/) (2026)

## Abstract (arXiv)

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.