Paper Link
Authors: Tianfang Zhang, Lei Li, Siying Cao, Tian Pu and Zhenming Peng
- MDFA dataset is available at MDvsFa cGan.
- SIRST dataset is available at SIRST.
- The SIRST Augment dataset: download from Google Drive or BaiduYun Drive with code
ojd4.
python train.py --net-name agpcnet_1 --batch-size 8 --save-iter-step 20 --dataset mdfapython train.py --net-name agpcnet_1 --batch-size 8 --save-iter-step 40 --dataset sirstaugpython train.py --net-name agpcnet_1 --batch-size 8 --save-iter-step 100 --dataset mergedpython inference.py --pkl-path {checkpoint path} --image-path {image path}python evaluation.py --dataset {dataset name}
--sirstaug-dir {base dir of sirstaug}
--mdfa-dir {base dir of MDFA}
--pkl-path {checkpoint path}| Methods | Data | Precision | Recall | mIoU | Fmeasure | AUC | Download |
|---|---|---|---|---|---|---|---|
| AGPCNet+ResNet18 | MDFA | 0.5939 | 0.7241 | 0.4843 | 0.6525 | 0.8682 | model |
| AGPCNet+ResNet18 | SIRST Aug | 0.8323 | 0.8542 | 0.7288 | 0.8431 | 0.9344 | model |
| AGPCNet+ResNet18 | Merged | 0.7453 | 0.8384 | 0.6517 | 0.7891 | 0.9194 | model |
Evaluation of model-driven algorithms based on traditional metrics refers [ISTD-python].
@article{zhang2023attention,
title={Attention-guided pyramid context networks for detecting infrared small target under complex background},
author={Zhang, Tianfang and Li, Lei and Cao, Siying and Pu, Tian and Peng, Zhenming},
journal={IEEE Transactions on Aerospace and Electronic Systems},
year={2023},
doi={10.1109/TAES.2023.3238703},
publisher={IEEE}
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent