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
收藏
页码:3698 / 3702
页数:5
相关论文
共 33 条
[1]  
[Anonymous], ABS170803088 CORR
[2]  
[Anonymous], 2016, CoRR
[3]  
[Anonymous], 2016, CORR
[4]  
[Anonymous], 2015, ABS150301640 CORR
[5]  
[Anonymous], 2016, CORR
[6]  
[Anonymous], 2011, ADV NEURAL INF PROCE
[7]  
[Anonymous], 2015, MXNET FLEXIBLE EFFIC
[8]  
[Anonymous], 2016, CORR
[9]  
[Anonymous], 2016, CORR
[10]  
[Anonymous], 2016, CORR