Recent works have made great progress in semantic segmentation by exploiting
contextual information in a local or global manner with dilated convolutions,
pyramid pooling or self-attention mechanism. In order to avoid potential
misleading contextual information aggregation in previous works, we propose a
class-wise dynamic graph convolution (CDGC) module to adaptively propagate
information. The graph reasoning is performed among pixels in the same class.
Based on the proposed CDGC module, we further introduce the Class-wise Dynamic
Graph Convolution Network(CDGCNet), which consists of two main parts including
the CDGC module and a basic segmentation network, forming a coarse-to-fine
paradigm. Specifically, the CDGC module takes the coarse segmentation result as
class mask to extract node features for graph construction and performs dynamic
graph convolutions on the constructed graph to learn the feature aggregation
and weight allocation. Then the refined feature and the original feature are
fused to get the final prediction. We conduct extensive experiments on three
popular semantic segmentation benchmarks including Cityscapes, PASCAL VOC 2012
and COCO Stuff, and achieve state-of-the-art performance on all three
benchmarks.

该论文提出基于类别的动态图卷积网络 CDGCNet，采用类别动态图卷积（CDGC）模块自适应地传递信息，获得了在 Cityscapes，PASCAL VOC 2012 和 COCO Stuff 等三个流行的语义分割基准上的 state-of-the-art 表现。