Home

Awesome

<img src="imgs/DSFD_logo.PNG" title="Logo" width="300" />

Update

Introduction

<p align='center'> <img src='./imgs/dsfd_video.gif' width=1000'/> </p>

In this repo, we propose a novel face detection network, named DSFD, with superior performance over the state-of-the-art face detectors. You can use the code to evaluate our DSFD for face detection.

For more details, please refer to our paper DSFD: Dual Shot Face Detector! or poster slide!

<p align='center'> <img src='./imgs/DSFD_framework.PNG' alt='DSFD Framework' width='1000px'> </p>

Our DSFD face detector achieves state-of-the-art performance on WIDER FACE and FDDB benchmark.

WIDER FACE

<p align='center'> <img src='./imgs/DSFD_widerface.PNG' alt='DSFD Widerface Performance' width='1000px'> </p>

FDDB

<p align='center'> <img src='./imgs/DSFD_fddb.PNG' alt='DSFD FDDB Performance' width='1000px'> </p>

Requirements

Getting Started

Installation

Clone the github repository. We will call the cloned directory as $DSFD_ROOT.

git clone xxxxxx/FaceDetection-DSFD.git
cd FaceDetection-DSFD
export CUDA_VISIBLE_DEVICES=0

Evaluation

  1. Download the images of WIDER FACE and FDDB to $DSFD_ROOT/data/.

  2. Download our DSFD model 微云 google drive trained on WIDER FACE training set to $DSFD_ROOT/weights/.

  3. Check out ./demo.py on how to detect faces using the DSFD model and how to plot detection results.

python demo.py [--trained_model [TRAINED_MODEL]] [--img_root  [IMG_ROOT]] 
               [--save_folder [SAVE_FOLDER]] [--visual_threshold [VISUAL_THRESHOLD]] 
    --trained_model      Path to the saved model
    --img_root           Path of test images
    --save_folder        Path of output detection resutls
    --visual_threshold   Confidence thresh
  1. Evaluate the trained model via ./widerface_val.py on WIDER FACE.
python widerface_val.py [--trained_model [TRAINED_MODEL]] [--save_folder [SAVE_FOLDER]] 
                         [--widerface_root [WIDERFACE_ROOT]]
    --trained_model      Path to the saved model
    --save_folder        Path of output widerface resutls
    --widerface_root     Path of widerface dataset

  1. Download the eval_tool to show the WIDERFACE performance.

  2. Evaluate the trained model via ./fddb_test.py on FDDB.

python widerface_test.py [--trained_model [TRAINED_MODEL]] [--split_dir [SPLIT_DIR]] 
                         [--data_dir [DATA_DIR]] [--det_dir [DET_DIR]]
    --trained_model      Path of the saved model
    --split_dir          Path of fddb folds
    --data_dir           Path of fddb all images
    --det_dir            Path to save fddb results
  1. Download the evaluation to show the FDDB performance.
  2. Lightweight DSFD is here.

Qualitative Results

<p align='center'> <img src='./imgs/DSFD_demo1.PNG' width='1000'/> </p> <p align='center'> <img src='./imgs/DSFD_demo2.PNG' width='1000'/> </p>

Citation

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

@inproceedings{li2018dsfd,
  title={DSFD: Dual Shot Face Detector},
  author={Li, Jian and Wang, Yabiao and Wang, Changan and Tai, Ying and Qian, Jianjun and Yang, Jian and Wang, Chengjie and Li, Jilin and Huang, Feiyue},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2019}
}

Contact

For any question, please file an issue or contact

Jian Li: swordli@tencent.com