A Tiny Object Detection Method Based on Explicit Semantic Guidance for Remote Sensing Images (IEEE GRSL 2024)
This repository contains python implementation of our paper ESG_TODNet.
- Linux
- Python 3.6+
- PyTorch 1.3+
- CUDA 9.2+
- GCC 5+
- MMCV
- cocoapi-aitod
Note that our ESG_TODNet is based on the MMDetection 2.24.1. Assume that your environment has satisfied the above requirements, please follow the following steps for installation.
git clone https://github.com/dyl96/ESG_TODNet.git
cd ESG_TODNet
pip install -r requirements/build.txt
python setup.py developDownload AI-TODv2 dataset
python tools/train.py configs_esg/ESG_TODNet/aitodv2_fcos_r50_p2_esg_3x.py
Please cite our paper if you find the work useful:
@ARTICLE{10462223,
author={Liu, Dongyang and Zhang, Junping and Qi, Yunxiao and Wu, Yinhu and Zhang, Ye},
journal={IEEE Geoscience and Remote Sensing Letters},
title={A Tiny Object Detection Method Based on Explicit Semantic Guidance for Remote Sensing Images},
year={2024},
volume={21},
number={},
pages={1-5},
doi={10.1109/LGRS.2024.3374418}}
@ARTICLE{10988878,
author={Liu, Dongyang and Zhang, Junping and Qi, Yunxiao and Xi, Yunqiao and Jin, Jing},
journal={IEEE Transactions on Geoscience and Remote Sensing},
title={Exploring Lightweight Structures for Tiny Object Detection in Remote Sensing Images},
year={2025},
volume={63},
number={},
pages={1-15},
doi={10.1109/TGRS.2025.3567345}}
@ARTICLE{10462223,
author={Liu, Dongyang and Zhang, Junping and Qi, Yunxiao and Wu, Yinhu and Zhang, Ye},
journal={IEEE Transactions on Geoscience and Remote Sensing},
title={Tiny Object Detection in Remote Sensing Images Based on Object Reconstruction and Multiple Receptive Field Adaptive Feature Enhancement},
year={2024},
volume={62},
number={},
pages={1-13},
doi={10.1109/TGRS.2024.3381774}}