Dense Relation Network: Learning Consistent and Context-Aware Representation for Semantic Image Segmentation
Authors:
- 1 October 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3698-3702
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.Keywords
This publication has 12 references indexed in Scilit:
- Semantic Segmentation via Structured Patch Prediction, Context CRF and Guidance CRF2017
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation2016
- Training Region-Based Object Detectors with Online Hard Example Mining2016
- Semantic Image Segmentation via Deep Parsing Network2015
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation2015
- Conditional Random Fields as Recurrent Neural Networks2015
- Fully convolutional networks for semantic segmentation2015
- The Role of Context for Object Detection and Semantic Segmentation in the Wild2014
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014