AFPN: Asymptotic Feature Pyramid Network for Object Detection (arXiv)

By Guoyu Yang, Jie Lei, Zhikuan Zhu, Siyu Cheng, Zunlei Feng, Ronghua Liang

This project is based on mmdetection.

Environment

mmengine==0.7.3
mmcv==2.0.0
mmdet==3.0.0
mmyolo==0.5.0

Install

Please refer to mmdetection for installation.

Dataset

AFPN
├── mmdetection
├── data
│   ├── coco
│   │   ├── annotations
│   │   ├── train2017
│   │   ├── val2017
│   │   ├── test2017
├── faster-rcnn_r50_afpn_1x_coco.py
├── train.py
├── test.py

Training

Single gpu for train:

CUDA_VISIBLE_DEVICES=0 python ./mmdetection/tools/train.py faster-rcnn_r50_afpn_1x_coco.py --work-dir ./weight/

Multiple gpus for train:

CUDA_VISIBLE_DEVICES=0,1 ./mmdetection/tools/dist_train.sh faster-rcnn_r50_afpn_1x_coco.py 2 --work-dir ./weight/

Train in pycharm: If you want to train in pycharm, you can run it in train.py.

see more details at mmdetection.

Testing

CUDA_VISIBLE_DEVICES=0 python ./mmdetection/tools/test.py faster-rcnn_r50_afpn_1x_coco.py <CHECKPOINT_FILE>

For example,

CUDA_VISIBLE_DEVICES=0 python ./mmdetection/tools/test.py faster-rcnn_r50_afpn_1x_coco.py ./weight/afpn_weight.pth

Test in pycharm: If you want to test in pycharm, you can run it in test.py.

see more details at mmdetection.

Results on MS COCO val2017

Citations

If you find AFPN useful in your research, please consider citing:

@article{yang2023afpn,
  title={AFPN: Asymptotic Feature Pyramid Network for Object Detection},
  author={Yang, Guoyu and Lei, Jie and Zhu, Zhikuan and Cheng, Siyu and Feng, Zunlei and Liang, Ronghua},
  journal={arXiv preprint arXiv:2306.15988},
  year={2023}
}

or

@article{yang2024asymptotic,
  title={Asymptotic Feature Pyramid Network for Labeling Pixels and Regions},
  author={Yang, Guoyu and Lei, Jie and Tian, Hao and Feng, Zunlei and Liang, Ronghua},
  journal={IEEE Transactions on Circuits and Systems for Video Technology},
  year={2024},
  publisher={IEEE}
}