/Super-BPD

Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation (CVPR 2020)

Primary LanguagePythonApache License 2.0Apache-2.0

Super-BPD for Fast Image Segmentation (CVPR 2020)

Introduction

We propose direction-based super-BPD, an alternative to superpixel, for fast generic image segmentation, achieving state-of-the-art real-time result.

Citation

Please cite the related works in your publications if it helps your research:


@InProceedings{Wan_2020_CVPR,
author = {Wan, Jianqiang and Liu, Yang and Wei, Donglai and Bai, Xiang and Xu, Yongchao},
title = {Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}

Prerequisite

  • pytorch >= 1.3.0
  • g++ 7

Dataset

Testing

  • Compile cuda code for post-process.
cd post_process
python setup.py install
  • Download the pre-trained PascalContext model and put it in the saved folder.

  • Test the model and results will be saved in the test_pred_flux/PascalContext folder.

  • SEISM is used for evaluation of image segmentation.

Training

python train.py --dataset PascalContext