DENSE RELATION NETWORK: LEARNING CONSISTENT AND CONTEXT-AWARE REPRESENTATION FOR SEMANTIC IMAGE SEGMENTATION

被引：0

作者：

Zhuang, Yueqing ^{[1
]}

Yang, Fan ^{[1
]}

Tao, Li ^{[1
]}

Ma, Cong ^{[1
]}

Zhang, Ziwei ^{[1
]}

Li, Yuan ^{[1
]}

Jia, Huizhu ^{[1
]}

Xie, Xiaodong ^{[1
]}

Gao, Wen ^{[1
]}

机构：

[1] Peking Univ, Natl Engn Lab Video Technol, Beijing 100871, Peoples R China

来源：

2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2018年

基金：

美国国家科学基金会;

关键词：

Image Semantic Segmentation; Context-Aware Representation; Context-Restricted Loss;

D O I：

暂无

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

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.

引用

页码：3698 / 3702

页数：5