README.md

---
license: apache-2.0
tags:
- salient-object-detection
- remote-sensing
- computer-vision
- multimodal
- pytorch
---

<a id="top"></a>
<div align="center">
  <h1>🚀 HFCNet: Heterogeneous Feature Collaboration Network for Salient Object Detection in Optical Remote Sensing Images</h1>

  <p>
    <b>Yutong Liu</b><sup>1</sup>&nbsp;
    <b>Mingzhu Xu</b><sup>1</sup>&nbsp;
    <b>Tianxiang Xiao</b><sup>1</sup>&nbsp;
    <b>Haoyu Tang</b><sup>1</sup>&nbsp;
    <b>Yupeng Hu</b><sup>1✉</sup>&nbsp;
    <b>Liqiang Nie</b><sup>1</sup>
  </p>

  <p>
    <sup>1</sup>Affiliation (Please update if needed)
  </p>
</div>

Official implementation of **HFCNet**, a Heterogeneous Feature Collaboration Network for Salient Object Detection (SOD) in Optical Remote Sensing Images.

🔗 **Journal:** IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2024  
🔗 **Task:** Salient Object Detection (SOD)  
🔗 **Framework:** PyTorch  

---

## 📌 Model Information

### 1. Model Name
**HFCNet** (Heterogeneous Feature Collaboration Network)

---

### 2. Task Type & Applicable Tasks
- **Task Type:** Salient Object Detection / Remote Sensing  
- **Core Task:** Salient object detection in optical remote sensing imagery  
- **Applicable Scenarios:**
  - Remote sensing scene understanding  
  - Aerial object detection  
  - Environmental monitoring  

---

### 3. Project Introduction

Salient Object Detection (SOD) in remote sensing images is challenging due to complex backgrounds, scale variations, and heterogeneous feature distributions.

**HFCNet** proposes a Heterogeneous Feature Collaboration framework, which:

- Integrates multi-level heterogeneous features  
- Enhances feature interaction and collaboration  
- Improves representation of salient objects across scales  
- Strengthens robustness against background interference  

---

### 4. Training Data Source

Supported datasets:

- ORSSD  
- EORSSD  
- ORSI  

---

## 🚀 Pre-trained Weights

### Initialization Weights

Download backbone weights:

- Swin Transformer  
- VGG16  

Place `.pth` files into:./pretrained


---

### Trained Weights

Download trained model weights:

- Baidu Cloud: https://pan.baidu.com/s/1bVC4uxf3xKhLRcC08EQKMQ?pwd=hfcn  

---

## 🚀 Training

1. Download datasets and pre-trained weights  
2. Prepare dataset path lists (.txt files)  
3. Update dataset paths in config files  

### Run training:

```bash
nohup python -u main.py --flag train --model_id HFCNet --config config/dataset_o.yaml --device cuda:0 > train_ORSSD.log &

nohup python -u main.py --flag train --model_id HFCNet --config config/dataset_e.yaml --device cuda:0 > train_EORSSD.log &

nohup python -u main.py --flag train --model_id HFCNet --config config/dataset_orsi.yaml --device cuda:0 > train_ORSI.log &

## 🚀 Testing
mkdir ./modelPTH-ORSSD
python main.py --flag test --model_id HFCNet --config config/dataset_o.yaml

mkdir ./modelPTH-EORSSD
python main.py --flag test --model_id HFCNet --config config/dataset_e.yaml 

mkdir ./modelPTH-ORSI
python main.py --flag test --model_id HFCNet --config config/dataset_orsi.yaml

## ⚠️ Notes
Designed for academic research
Performance depends on dataset characteristics
Requires GPU for efficient training

## 📝Citation
@ARTICLE{HFCNet,
  author={Liu, Yutong and Xu, Mingzhu and Xiao, Tianxiang and Tang, Haoyu and Hu, Yupeng and Nie, Liqiang},
  journal={IEEE Transactions on Geoscience and Remote Sensing}, 
  title={Heterogeneous Feature Collaboration Network for Salient Object Detection in Optical Remote Sensing Images}, 
  year={2024},
  volume={62},
  pages={1-14}
}