Dense Relation Network: Learning Consistent and Context-Aware Representation for Semantic Image Segmentation

Yueqing Zhuang, Fan Yang, Li Tao, Cong Ma, Ziwei Zhang, Yuan Li, Huizhu Jia, Xiaodong Xie, Wen GaoICIP 2018 · OpenReview

Abstract

Semantic image segmentation, which aims at assigning pixel-wise category, is one of challenging image understanding problems. Global context plays an important role on local pixel-wise category assignment. To make the best of global context, in this paper, we propose dense relation network (DRN) and context-restricted loss (CRL) to aggregate global and local information. DRN uses Recurrent Neural Network (RNN) with different skip lengths in spatial directions to get context-aware representations while CRL helps aggregate them to learn consistency. Compared with previous methods, our proposed method takes full advantage of hierarchical contextual representations to produce high-quality results. Extensive experiments demonstrate that our method achieves significant state-of-the-art performances on Cityscapes and Pascal Context benchmarks, with mean-IoU of 82.8% and 49.0% respectively.
BibTeX
@inproceedings{zhuang2018dense,
  author = {Yueqing Zhuang and Fan Yang and Li Tao and Cong Ma and Ziwei Zhang and Yuan Li and Huizhu Jia and Xiaodong Xie and Wen Gao},
  title = {{Dense Relation Network: Learning Consistent and Context-Aware Representation for Semantic Image Segmentation}},
  booktitle = {ICIP},
  year = {2018},
  url = {https://openreview.net/forum?id=PlKOog0Cdh},
}

Loading related content...

Figure