Skip to content

Latest commit

 

History

History
23 lines (21 loc) · 1019 Bytes

README.md

File metadata and controls

23 lines (21 loc) · 1019 Bytes

CRF-EfficientUNet

This repository is an official Keras implementation of the paper "CRF-EfficientUNet: an improved UNet framework for polyp segmentation in colonoscopy images with combined asymmetric loss function and CRF-RNN layer" paper from IEEE Acess 2021.

Prerequisites

  1. Linux or OSX

  2. NVIDIA GPU + CUDA CuDNN (CPU mode and CUDA without CuDNN may work with minimal modification, but untested)

  3. tensorflow==1.13.1

  4. numpy==1.18.5

  5. Keras==2.2.4

  6. opencv-python==4.3.0

Cite

If you find our work useful in your research or publication, please cite our work:

@article{thanh2021crf,
  title={CRF-EfficientUNet: An Improved UNet Framework for Polyp Segmentation in Colonoscopy Images With Combined Asymmetric Loss Function and CRF-RNN Layer},
  author={Thanh, Nguyen Chi and Long, Tran Quoc and Hong, Le Thi Thu},
  journal={IEEE Access},
  volume={9},
  pages={156987--157001},
  year={2021},
  publisher={IEEE}
}