/AC-FPN

Implement of paper 《Attention-guided Context Feature Pyramid Network for Object Detection》

Primary LanguagePythonApache License 2.0Apache-2.0

Attention-guided Context Feature Pyramid Network for Object Detection

This repository re-implements AC-FPN on the base of Detectron-Cascade-RCNN. Please follow Detectron on how to install and use this repo.

This repo has released CEM module without AM module, but we can get higher performance than the implementation of pytorch in paper. Also, thanks to the power of detectron, this repo is faster in training and inference.

The implementation of CEM is very simple, which is less than 200 lines code, but it can boost the performance almost 3% AP in FPN(resnet50).

AC-FPN

AC-FPN can be readily plugged into existing FPN-based models and improve performance. architecture

Visualization of object detection. Both models are built upon ResNet-50 on COCO minival. detection

Results of Mask R-CNN with (w) and without (w/o) our modules built upon ResNet-50 on COCO minival. segmentation

More detail in paper.

Benchmarking

Because of the proposed architecture, We have better performance on most of FPN-base methods, especially on large objects. segmentation

The result of coco test-dev(team Neptune). rank

Mask R-CNN with Bells & Whistles

        backbone         type lr
schd
im/
gpu
box
AP
box
AP50
box
AP75
X-152-32x8d-FPN-IN5k-baseline Mask s1x 1 48.1 68.3 52.9
X-152-32x8d-FPN-IN5k-cascade Mask s1x 1 50.2 68.2 55.0
X-152-32x8d-FPN-IN5k-acfpn(only CEM) Mask s1x 1 51.9 70.4 57.0

Citation

If you use our code/model/data, please site our paper:

@article{cao2020attention,
  title={Attention-guided Context Feature Pyramid Network for Object Detection},
  author={Cao, Junxu and Chen, Qi and Guo, Jun and Shi, Ruichao},
  journal={arXiv},
  pages={arXiv--2005},
  year={2020}
}

and Cascadercnn:

@inproceedings{cai18cascadercnn,
  author = {Zhaowei Cai and Nuno Vasconcelos},
  Title = {Cascade R-CNN: Delving into High Quality Object Detection},
  booktitle = {CVPR},
  Year  = {2018}
}

and Detectron:

@misc{Detectron2018,
  author =       {Ross Girshick and Ilija Radosavovic and Georgia Gkioxari and
                  Piotr Doll\'{a}r and Kaiming He},
  title =        {Detectron},
  howpublished = {\url{https://github.com/facebookresearch/detectron}},
  year =         {2018}
}