Published April 27, 2023 | Version v1

CASENet: Deep Category-Aware Semantic Edge Detection

  • 1. NVIDIA Research
  • 2. New York University (NYU)
  • 3. Google Research, University of Utah

Description

Introduction

This dataset includes initial and trained model weights (caffemodel files) for SBD/Cityscapes datasets which is used in our CASENet software available (https://github.com/merlresearch/CASENet).

Citation

If you use the data, please cite the following TR2017-100:

@inproceedings{Yu2017jul,
  author = {Yu, Zhiding and Feng, Chen and Liu, Ming-Yu and Ramalingam, Srikumar},
  title = {CASENet: Deep Category-Aware Semantic Edge Detection},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = 2017,
  month = jul,
  doi = {10.1109/CVPR.2017.191},
  url = {https://www.merl.com/publications/TR2017-100}
}

Copyright and License
The CASENet dataset is released under CC-BY-SA-4.0 license.


All data:

Created by Mitsubishi Electric Research Laboratories (MERL), 2017, 2023
 
SPDX-License-Identifier: CC-BY-SA-4.0


 

Files

CASENet.zip

Files (1.3 GB)

Name Size
md5:9a7cb24d85b2a75aa9efe6ccd22bcd75
1.3 GB Preview Download