41b2ea1ff9
- 在 net.py 中引入 SMFA 组件
- 优化 BasicLayer 类的前向传播逻辑
- 添加 SMFA、DynamicFilter 和 UFFC 组件的实现
- 使用SMFA替代Pooling
self.WTConv2d = WTConv2d(dim, dim)
self.norm1 = LayerNorm(dim, 'WithBias')
self.token_mixer = SMFA(dim=dim)
# self.token_mixer = Pooling(kernel_size=pool_size) # vits是msa，MLPs是mlp，这个用pool来替代
self.norm2 = LayerNorm(dim, 'WithBias')
mlp_hidden_dim = int(dim * mlp_ratio)
self.poolmlp = PoolMlp(in_features=dim, hidden_features=mlp_hidden_dim,
act_layer=act_layer, drop=drop)
|
||
|---|---|---|
| .idea | ||
| componets | ||
| image | ||
| logs | ||
| mamba_ssm | ||
| models | ||
| test_img | ||
| test_result | ||
| utils | ||
| .gitignore | ||
| ConvSSM.py | ||
| dataprocessing.py | ||
| net_cddfuse.py | ||
| net_me.py | ||
| net.py | ||
| PFCFuse_IVF.pth | ||
| README.md | ||
| requirement.txt | ||
| status.md | ||
| test_IVF.py | ||
| test_sar.py | ||
| train.py | ||
| trainExe.py | ||
PFCFuse: A Poolformer and CNN fusion network for Infrared-Visible Image Fusion
The implementation of our paper "PFCFuse: A Poolformer and CNN fusion network for Infrared-Visible Image Fusion".
Recommended Environment:
python=3.8
torch=1.12.1+cu113
scipy=1.9.3
scikit-image=0.19.2
scikit-learn=1.1.3
tqdm=4.62.0
Network Architecture:
Our PFCFuse is implemented in net.py.
Training:
Data preprocessing
Run
python dataprocessing.py
Model training
Run
python train.py
Testing:
Run
python test_IVF.py
相关工作
@inproceedings{zhao2023cddfuse,
title={Cddfuse: Correlation-driven dual-branch feature decomposition for multi-modality image fusion},
author={Zhao, Zixiang and Bai, Haowen and Zhang, Jiangshe and Zhang, Yulun and Xu, Shuang and Lin, Zudi and Timofte, Radu and Van Gool, Luc},
booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
pages={5906--5916},
year={2023}
}