Home

Awesome

PedesFormer

PedesFormer is a MMDetection and SwinTransformer based repository. It is a successor to our earlier work Pedestron. PedesFormer, focuses on the adavancement of reseach on pedestrian detection using transformer networks.

<img title="Amsterdam" src="gifs/1.gif" width="400" /> <img title="Amsterdam" src="gifs/2.gif" width="400"/> <img title="Amsterdam" src="gifs/3.gif" width="400"/> <img title="Amsterdam" src="gifs/4.gif" width="400"/>

:fire: Updates :fire:

Pretrained Models

Benchmarking

Benchmarking of pre-trained models on pedestrian detection datasets (autonomous driving)

BackboneDatasetBackboneConfigurationReasonableHeavy
[Cascade Mask R-CNN]CityPersonsSwin - TransformerConfig9.236.9
[Cascade Mask R-CNN]EuroCity PersonsSwin - Transformer--
[Cascade Mask R-CNN]Crowd HumanSwin - Transformer--

More Pre-trained models are coming soon.

Installation

For installation, please see this.

Citation

Please cite the following works

CVPR2021

@InProceedings{Hasan_2021_CVPR,
    author    = {Hasan, Irtiza and Liao, Shengcai and Li, Jinpeng and Akram, Saad Ullah and Shao, Ling},
    title     = {Generalizable Pedestrian Detection: The Elephant in the Room},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {11328-11337}
}

ArXiv 2022

@article{hasan2022pedestrian,
  title={Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond},
  author={Hasan, Irtiza and Liao, Shengcai and Li, Jinpeng and Akram, Saad Ullah and Shao, Ling},
  journal={arXiv preprint arXiv:2201.03176},
  year={2022}
}