ICNet for Real-Time Semantic Segmentation on High-Resolution Images

Hengshuang Zhao, Xiaojuan Qi, Xiaoyong Shen, Jianping Shi, Jiaya Jia

ECCV 2018

doi:10.1007/978-3-030-01219-9_25 /eccv/2018/zhao2018eccv-icnet/

Abstract

We focus on the challenging task of real-time semantic segmentation in this paper. It finds many practical applications and yet is with fundamental difficulty of reducing a large portion of computation for pixel-wise label inference. We propose an image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to address this challenge. We provide in-depth analysis of our framework and introduce the cascade feature fusion unit to quickly achieve high-quality segmentation. Our system yields real-time inference on a single GPU card with decent quality results evaluated on challenging datasets like Cityscapes, CamVid and COCO-Stuff.

PDF ECCV Semantic Scholar

Cite

Text

Zhao et al. "ICNet for Real-Time Semantic Segmentation on High-Resolution Images." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01219-9_25

Markdown

[Zhao et al. "ICNet for Real-Time Semantic Segmentation on High-Resolution Images." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/zhao2018eccv-icnet/) doi:10.1007/978-3-030-01219-9_25

BibTeX

@inproceedings{zhao2018eccv-icnet,
  title     = {{ICNet for Real-Time Semantic Segmentation on High-Resolution Images}},
  author    = {Zhao, Hengshuang and Qi, Xiaojuan and Shen, Xiaoyong and Shi, Jianping and Jia, Jiaya},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2018},
  doi       = {10.1007/978-3-030-01219-9_25},
  url       = {https://mlanthology.org/eccv/2018/zhao2018eccv-icnet/}
}