Mixed context networks for semantic segmentation

Semantic segmentation is challenging as it requires both object-level information and pixel-level accuracy. Recently, FCN-based systems gained great improvement in this area. Unlike classification networks, combining features of different layers plays an important role in these dense prediction models, as these features contains information of different levels. A number of models have been proposed to show how to use these features. However, what is the best architecture to make use of features of different layers is still a question. In this paper, we propose a module, called mixed context network, and show that our presented system outperforms most existing semantic segmentation systems by making use of this module.

• Publication year

  2016

• Venue

  arXiv.org

• Publication date

  2016-10-19

• Fields of study

  Computer Science

• Identifiers
  arXiv 1610.05854
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Semantic Understanding of Scenes Through the ADE20K Dataset

  2016influential reference
• Learning to Refine Object Segments

  2016influential reference
• The Importance of Skip Connections in Biomedical Image Segmentation

  2016cited by this paper
• PixelNet: Towards a General Pixel-level Architecture

  2016cited by this paper
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

  2016cited by this paper
• Conditional Random Fields as Recurrent Neural Networks

  2015cited by this paper
• Multi-Scale Context Aggregation by Dilated Convolutions

  2015influential reference
• Attention to Scale: Scale-Aware Semantic Image Segmentation

  2015cited by this paper
• Hypercolumns for object segmentation and fine-grained localization

  2014cited by this paper
• Microsoft COCO: Common Objects in Context

  2014cited by this paper
• Very Deep Convolutional Networks for Large-Scale Image Recognition

  2014cited by this paper
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

  2014cited by this paper
• Caffe: Convolutional Architecture for Fast Feature Embedding

  2014cited by this paper
• Fully convolutional networks for semantic segmentation

  2014influential reference
• Semantic contours from inverse detectors

  2011cited by this paper
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

  2011cited by this paper

• Your Image Is My Video: Reshaping the Receptive Field via Image-to-Video Differentiable AutoAugmentation and Fusion

  2024cites this paper
• An enhancement model based on dense atrous and inception convolution for image semantic segmentation

  2022cites this paper
• Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond

  2021cites this paper
• Multi-scale Context Intertwining for Semantic Segmentation

  2018cites this paper
• Vortex Pooling: Improving Context Representation in Semantic Segmentation

  2018influential citation
• Rethinking Atrous Convolution for Semantic Image Segmentation

  2017influential citation
• Understanding Convolution for Semantic Segmentation

  2017cites this paper
• Per-Pixel Feedback for improving Semantic Segmentation

  2017cites this paper
• Designing Convolutional Neural Networks for Urban Scene Understanding

  2017cites this paper