Contextual deconvolution network for semantic segmentation

作者：

Highlights：

• A Contextual Deconvolution Network (CDN) is proposed to enhance the representation power of the decoder network.

• A channel contextual module is proposed to model the channel interdependencies of features, which imposes a global semantic control.

• A spatial contextual module is introduced to model the spatial interdependencies, making the features more expressive on some local regions.

• The proposed method achieves competitive performance on PASCAL VOC 2012, ADE20K, PASCAL-Context and Cityscapes dataset, and new state-of-the-art performance on PASCAL-Context dataset.

摘要

•A Contextual Deconvolution Network (CDN) is proposed to enhance the representation power of the decoder network.•A channel contextual module is proposed to model the channel interdependencies of features, which imposes a global semantic control.•A spatial contextual module is introduced to model the spatial interdependencies, making the features more expressive on some local regions.•The proposed method achieves competitive performance on PASCAL VOC 2012, ADE20K, PASCAL-Context and Cityscapes dataset, and new state-of-the-art performance on PASCAL-Context dataset.

论文关键词：Semantic segmentation,Deconvolution network,Channel contextual module,Spatial contextual module

论文评审过程：Received 11 June 2018, Revised 24 August 2019, Accepted 4 December 2019, Available online 3 January 2020, Version of Record 9 January 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107152