Dual Graph Convolutional Network for Semantic Segmentation

Abstract

Exploiting long-range contextual information is key for pixel-wise prediction tasks such as semantic segmentation. In contrast to previous work that uses multi-scale feature fusion or dilated convolutions, we propose a novel graph-convolutional network (GCN) to address this problem. Our Dual Graph Convolutional Network (DGCNet) models the global context of the input feature by modelling two orthogonal graphs in a single framework. The first component models spatial relationships between pixels in the image, whilst the second models interdependencies along the channel dimensions of the network's feature map. This is done efficiently by projecting the feature into a new, lower-dimensional space where all pairwise interactions can be modelled, before reprojecting into the original space. Our simple method provides substantial benefits over a strong baseline and achieves state-of-the-art results on both Cityscapes (82.0% mean IoU) and Pascal Context (53.7% mean IoU) datasets. Code and models are made available to foster any further research (\url{https://github.com/lxtGH/GALD-DGCNet}).

arXiv commentBMVC 2019. Code is available at \url{https://github.com/lxtGH/GALD-DGCNet}

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Conditional Random Fields as Recurrent Neural Networks
• ParseNet: Looking Wider to See Better
• OCNet: Object Context Network for Scene Parsing
• Dual Attention Network for Scene Segmentation
• Semantic Understanding of Scenes through the ADE20K Dataset
• Global Aggregation then Local Distribution in Fully Convolutional Networks
• Graph-Based Global Reasoning Networks
• Vector-relation configurations and plabic graphs

Cited by in corpus (16)

• Unsupervised Scene Adaptation with Memory Regularization in vivo
• Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
• Fine-Grained Crowd Counting
• Bipartite Graph Reasoning GANs for Person Image Generation
• AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsing
• Global Aggregation then Local Distribution for Scene Parsing
• Vision Transformers: From Semantic Segmentation to Dense Prediction
• Graph-Segmenter: Graph Transformer with Boundary-aware Attention for Semantic Segmentation
• BI-GCN: Boundary-Aware Input-Dependent Graph Convolution Network for Biomedical Image Segmentation
• PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation
• Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image
• Edge-aware Graph Representation Learning and Reasoning for Face Parsing
• AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning
• TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency
• Graph-based Pyramid Global Context Reasoning with a Saliency-aware Projection for COVID-19 Lung Infections Segmentation
• Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation