wutianyiRosun / CGNet

CGNet: A Light-weight Context Guided Network for Semantic Segmentation [IEEE Transactions on Image Processing 2020]

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Introduction

The demand of applying semantic segmentation model on mobile devices has been increasing rapidly. Current state-of-the-art networks have enormous amount of parameters, hence unsuitable for mobile devices, while other small memory footprint models follow the spirit of classification network and ignore the inherent characteristic of semantic segmentation. To tackle this problem, we propose a novel Context Guided Network (CGNet), which is a light-weight and efficient network for semantic segmentation. We first propose the Context Guided (CG) block, which learns the joint feature of both local feature and surrounding context, and further improves the joint feature with the global context. Based on the CG block, we develop CGNet which captures contextual information in all stages of the network and is specially tailored for increasing segmentation accuracy. CGNet is also elaborately designed to reduce the number of parameters and save memory footprint. Under an equivalent number of parameters, the proposed CGNet significantly outperforms existing segmentation networks. Extensive experiments on Cityscapes and CamVid datasets verify the effectiveness of the proposed approach. Specifically, without any post-processing and multi-scale testing, the proposed CGNet achieves 64.8% mean IoU on Cityscapes with less than 0.5 M parameters.

Installation

  1. Install PyTorch
  • Env: PyTorch_0.4; cuda_9.2; cudnn_7.5; python_3.6
  1. Clone the repository
    git clone https://github.com/wutianyiRosun/CGNet.git 
    cd CGNet
  2. Dataset
├── cityscapes_test_list.txt
├── cityscapes_train_list.txt
├── cityscapes_trainval_list.txt
├── cityscapes_val_list.txt
├── cityscapes_val.txt
├── gtCoarse
│   ├── train
│   ├── train_extra
│   └── val
├── gtFine
│   ├── test
│   ├── train
│   └── val
├── leftImg8bit
│   ├── test
│   ├── train
│   └── val
├── license.txt
  • Download the Camvid dataset. It should have this basic structure.
├── camvid_test_list.txt
├── camvid_train_list.txt
├── camvid_trainval_list.txt
├── camvid_val_list.txt
├── test
├── testannot
├── train
├── trainannot
├── val
└── valannot

Train your own model

For Cityscapes

  1. training on train set
python cityscapes_train.py --gpus 0,1 --dataset cityscapes --train_type ontrain --train_data_list ./dataset/list/Cityscapes/cityscapes_train_list.txt --max_epochs 300
  1. training on train+val set
python cityscapes_train.py --gpus 0,1 --dataset cityscapes --train_type ontrainval --train_data_list ./dataset/list/Cityscapes/cityscapes_trainval_list.txt --max_epochs 350
  1. Evaluation (on validation set)
python cityscapes_eval.py --gpus 0 --val_data_list ./dataset/list/Cityscapes/cityscapes_val_list.txt --resume ./checkpoint/cityscapes/CGNet_M3N21bs16gpu2_ontrain/model_cityscapes_train_on_trainset.pth
  1. Testing (on test set)
python cityscapes_test.py --gpus 0 --test_data_list ./dataset/list/Cityscapes/cityscapes_test_list.txt --resume ./checkpoint/cityscapes/CGNet_M3N21bs16gpu2_ontrainval/model_cityscapes_train_on_trainvalset.pth
  1. Running time on Tesla V100 (single card single batch)
56.8 ms with command "torch.cuda.synchronize()"
20.0 ms w/o command "torch.cuda.synchronize()"

For Camvid

  1. training on train+val set
python camvid_train.py
  1. testing (on test set)
python camvid_test.py

Citation

If CGNet is useful for your research, please consider citing:

  @article{wu2020cgnet,
  title={Cgnet: A light-weight context guided network for semantic segmentation},
  author={Wu, Tianyi and Tang, Sheng and Zhang, Rui and Cao, Juan and Zhang, Yongdong},
  journal={IEEE Transactions on Image Processing},
  volume={30},
  pages={1169--1179},
  year={2020},
  publisher={IEEE}
}

License

This code is released under the MIT License. See LICENSE for additional details.

Thanks to the Third Party Libs

https://github.com/speedinghzl/Pytorch-Deeplab.

About

CGNet: A Light-weight Context Guided Network for Semantic Segmentation [IEEE Transactions on Image Processing 2020]

License:MIT License


Languages

Language:Python 100.0%