PRBNet PyTorch

This is the reference PyTorch implementation for training and testing single-shot object detection and oriented bounding boxes models using the method described in

Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection

Ping-Yang, Chen, Ming-Ching Chang, Jun-Wei Hsieh, and Yong-Sheng Chen

TIP 2021 (arXiv pdf)

Performance

MS COCO

P5 Model

Model	Test Size	AP^test	AP₅₀^test	AP₇₅^test	AP_s^test	Model Description
YOLOX-x	640	51.5%	-	-	-	-
YOLOv7	640	51.4%	69.7%	55.9%	31.8%	yaml

YOLOv4-PRB-CSP	640	51.8%	70.0%	56.7%	32.6%	yaml
YOLOv7-PRB	640	52.5%	70.4%	57.2%	33.4%	yaml

P6 Model

Model	Test Size	AP^test	AP₅₀^test	AP₇₅^test	FLOPs	Params (M)	Model Description
YOLOv7-D6	1280	56.6%	74.0%	61.8%	806.8G	154.7M
YOLOv7-E6E	1280	56.8%	74.4%	62.1%	843.2G	151.7M

PRB-FPN6-L	1280	55.9%	73.7%	61.1%	195.3G	137.5M	yaml

If you find our work useful in your research please consider citing our paper:

@ARTICLE{9603994,
  author={Chen, Ping-Yang and Chang, Ming-Ching and Hsieh, Jun-Wei and Chen, Yong-Sheng},
  journal={IEEE Transactions on Image Processing}, 
  title={Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection}, 
  year={2021},
  volume={30},
  number={},
  pages={9099-9111},
  doi={10.1109/TIP.2021.3118953}}

If you find the backbone also well-done in your research, please consider citing the CSPNet. Most of the credit goes to Dr. Wang:

@inproceedings{wang2020cspnet,
  title={{CSPNet}: A New Backbone That Can Enhance Learning Capability of {CNN}},
  author={Wang, Chien-Yao and Mark Liao, Hong-Yuan and Wu, Yueh-Hua and Chen, Ping-Yang and Hsieh, Jun-Wei and Yeh, I-Hau},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  pages={390--391},
  year={2020}
}

Acknowledgement