Contextual deconvolution network for semantic segmentation

•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.