Skip to content
Semantic Image Segmentation by Scale-Adaptive Networks (TIP 2019)
Python
Branch: master
Clone or download
Latest commit 97fdd26 Sep 15, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
config init repo Aug 9, 2018
list init repo Aug 9, 2018
seg_layer init repo Aug 9, 2018
tools init repo Aug 9, 2018
LICENSE Create LICENSE Aug 9, 2018
README.md Update README.md Sep 14, 2019

README.md

Semantic Image Segmentation by Scale-Adaptive Networks

By Zilong Huang, Chunyu Wang, Xinggang Wang, Wenyu Liu and Jingdong Wang.

This code is a implementation of the experiments in the paper Semantic Image Segmentation by Scale-Adaptive Networks, which is accepted by Transactions on Image Processing. The code is developed based on the Caffe framework.

License

SAN is released under the MIT License (refer to the LICENSE file for details).

Citing SANet

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

@article{huang2019sanet,
    title={Semantic Image Segmentation by Scale-Adaptive Networks},
    author={Huang, Zilong and Wang, Chunyu and Wang, Xinggang and Liu, Wenyu and Wang, Jingdong},
    journal={IEEE Transactions on Image Processing},
    year={2019},
    publisher={IEEE}
}

Installing dependencies

  • caffe (deeplabv2 version): deeplabv2 caffe installation instructions are available at https://bitbucket.org/aquariusjay/deeplab-public-ver2. Note, you need to compile caffe with python wrapper and support for python layers. Then add the caffe python path into tools/findcaffe.py.

Training the SAN model

  • Run:
      $ python tools/train.py --solver YOUR_SOLVER --weight IMAGENET_PRETRAINED_MODEL --gpu GPU_ID

The corresponding solver files and input image lists are put in config and list floders.

Acknowledgment

The work was mainly done during an internship at MSRA.

You can’t perform that action at this time.