• Home
  • Search
  • LSRFormer: Efficient Transformer Supply Convolutional Neural Networks With Global Information for Aerial Image Segmentation
  • Cite Icon32
  • https://doi.org/10.1109/tgrs.2024.3366709Copy DOI Icon

LSRFormer: Efficient Transformer Supply Convolutional Neural Networks With Global Information for Aerial Image Segmentation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Both local context and global context information are essential for the semantic segmentation of aerial images. Convolutional Neural Networks (CNNs) can capture local context information well but cannot model the global dependencies. Vision transformers (ViTs) are good at extracting global information but cannot retain the spatial details well. In order to leverage the advantages of these two paradigms, we integration them in one model in this study. However, global token interaction of ViT brings high computational cost, which makes it difficult to apply to large-sized aerial images. To handle this problem, we propose a novel efficient ViT block named long-short-range transformer (LSRFormer). Instead of mainstream ViTs designed as backbones, LSRFormer is a pre-training-free and plug-and-play module to be appended after CNN stages to supplement the global information. It is composed of long-range self-attention (LR-SA), short-range self-attention (SR-SA), and multi-scale-convolutional feed-forward-network (MSC-FFN). LR-SA establishes long-range dependencies at the junction of the windows and SR-SA diffuses the long-range information from window boundary to internal. MSC-FFN can capture multi-scale information inside the ViT block. We append LSRFormer block after each CNN stage of a pure convolutional network to build a model named ConvLSR-Net. Compared with existing models which combining CNN and ViTs, our model can learn both local and global representation at all stages of the model. In particular, ConvLSR-Net achieves state-of-the-art (SOTA) results on four challenging aerial image segmentation benchmarks, including iSAID, LoveDA, ISPRS Potsdam and Vaihingen. Code has been released at https://github.com/stdcoutzrh/ConvLSR-Net.

Similar Papers
  • PDF
  • Research Article

HDAM: Heuristic Difference Attention Module for Convolutional Neural Networks

  • Jan 01, 2022
  • Journal on Internet of Things
  • Yu Xue +1
  • Research Article
  • Citations13

GLFFNet: Global–Local Feature Fusion Network for High-Resolution Remote Sensing Image Semantic Segmentation

  • Mar 14, 2025
  • Remote Sensing
  • Saifeng Zhu +4
  • Research Article
  • Citations104

Semantic Segmentation of Aerial Images With Shuffling Convolutional Neural Networks

  • Feb 01, 2018
  • IEEE Geoscience and Remote Sensing Letters
  • Kaiqiang Chen +5
  • Research Article
  • Citations12

A scene segmentation algorithm combining the body and the edge of the object

  • Dec 01, 2021
  • Information Processing & Management
  • Xianfeng Ou +4
  • Book Chapter
  • Citations194

Keyword Extraction Using Support Vector Machine

  • Jan 01, 2006
  • Kuo Zhang +3
  • Research Article
  • Citations9

AfaMamba: Adaptive Feature Aggregation With Visual State Space Model for Remote Sensing Images Semantic Segmentation

  • Jan 01, 2025
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Hongkun Chen +2
  • Research Article
  • Citations27

GC–HGNN: A global-context supported hypergraph neural network for enhancing session-based recommendation

  • Mar 01, 2022
  • Electronic Commerce Research and Applications
  • Dunlu Peng +1
  • Conference Article
  • Citations9

Self-Mutating Network for Domain Adaptive Segmentation of Aerial Images

  • Oct 01, 2021
  • Kyungsu Lee +2
  • PDF
  • Research Article
  • Citations2

Few-Shot Object Detection with Local Feature Enhancement and Feature Interrelation

  • Sep 25, 2023
  • Electronics
  • Hefeng Lai +1
  • Conference Article
  • Citations1

Document-Level Joint Biomedical Event Extraction Model Using Hypergraph Convolutional Networks

  • Oct 09, 2022
  • Jinghao Gong +3
  • Research Article
  • Citations134

Multi-scale deep context convolutional neural networks for semantic segmentation

  • Apr 19, 2018
  • World Wide Web
  • Quan Zhou +6
  • PDF
  • Research Article
  • Citations281

Segment-before-Detect: Vehicle Detection and Classification through Semantic Segmentation of Aerial Images

  • Apr 13, 2017
  • Remote Sensing
  • Nicolas Audebert +2
  • Book Chapter
  • Citations34

Learning to Predict Context-Adaptive Convolution for Semantic Segmentation

  • Jan 01, 2020
  • Jianbo Liu +4
  • PDF
  • Research Article
  • Citations14

MLCRNet: Multi-Level Context Refinement for Semantic Segmentation in Aerial Images

  • Mar 20, 2022
  • Remote Sensing
  • Zhifeng Huang +2
  • Conference Article
  • Citations53

Collaboratively Improving Topic Discovery and Word Embeddings by Coordinating Global and Local Contexts

  • Aug 04, 2017
  • Guangxu Xun +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.