Progressive Feature Fusion Framework Based on Graph Convolutional Network for Remote Sensing Scene Classification

Model

Instructions

Please download the folder gcn_library, model.py and model_library.py.

Requirements

Pytorch 1.7.0, timm 0.3.2, torchprofile 0.0.4, apex

Acknowledgement

This repo partially uses code from deep_gcns_torch, timm and vig.

Citation

@ARTICLE{10381852,
  author={Zhang, Chongyang and Wang, Bin},
  journal={IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}, 
  title={Progressive Feature Fusion Framework Based on Graph Convolutional Network for Remote Sensing Scene Classification}, 
  year={2024},
  volume={17},
  number={},
  pages={3270-3284},
  keywords={Feature extraction;Scene classification;Data mining;Transformers;Semantics;Convolution;Remote sensing;Feature fusion;graph convolutional network (GCN);graph learning;remote sensing (RS);scene classification},
  doi={10.1109/JSTARS.2024.3350129}}