ACRNet(Published in IEEE-GRSL 2021): Multilevel Feature Fusion Networks With Adaptive Channel Dimensionality Reduction for Remote Sensing Scene Classification
Multilevel Feature Fusion Networks With Adaptive Channel Dimensionality Reduction for Remote Sensing Scene Classification[Paper link]
- Data preparation:
split.py
dataset|——train
|——Airport
|——BareLand
|——....
|——Viaduct
|——val
|——Airport
|——BareLand
|——....
|——Viaduct
- run
train.py
to train the model confusionmatrix.py
for drawing
UC Merced Land Use Dataset:
http://weegee.vision.ucmerced.edu/datasets/landuse.html
AID Dataset:
https://captain-whu.github.io/AID/
NWPU RESISC45:
http://www.escience.cn/people/JunweiHan/NWPU-RESISC45.html
- Ubuntu 16.04
- cuda 10.0
- pytorch 1.0.1
- opencv 3.4
Please cite our paper if you find the work useful:
@ARTICLE{9399658,
author={Wang, Xin and Duan, Lin and Shi, Aiye and Zhou, Huiyu},
journal={IEEE Geoscience and Remote Sensing Letters},
title={Multilevel Feature Fusion Networks With Adaptive Channel Dimensionality Reduction for Remote Sensing Scene Classification},
year={2021},
volume={},
number={},
pages={1-5},
doi={10.1109/LGRS.2021.3070016}}