Skip to content

Latest commit

 

History

History
executable file
·
30 lines (22 loc) · 1.75 KB

File metadata and controls

executable file
·
30 lines (22 loc) · 1.75 KB

DeepLab

Introduction

DeepLab is a state-of-art deep learning system for semantic image segmentation built on top of Caffe.

It combines densely-computed deep convolutional neural network (CNN) responses with densely connected conditional random fields (CRF).

This distribution provides a publicly available implementation for the key model ingredients first reported in an arXiv paper, accepted in revised form as conference publication to the ICLR-2015 conference. It also contains implementations for methods supporting model learning using only weakly labeled examples, described in a second follow-up arXiv paper. Please consult and consider citing the following papers:

@inproceedings{chen14semantic,
  title={Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs},
  author={Liang-Chieh Chen and George Papandreou and Iasonas Kokkinos and Kevin Murphy and Alan L Yuille},
  booktitle={ICLR},
  url={http://arxiv.org/abs/1412.7062},
  year={2015}
}

@inproceedings{papandreou15weak,
  title={Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation},
  author={George Papandreou and Liang-Chieh Chen and Kevin Murphy and Alan L Yuille},
  url={http://arxiv.org/abs/1502.02734},
  year={2015}
}

Performance

At the time of its release, DeepLab is the state-of-art method on semantic image segmentation on the challenging PASCAL VOC-2012 image segmentation task, with the latest variant achieving 72.7% mean IoU on the test set -- see the leaderboard.