Reviews: Symbolic Graph Reasoning Meets Convolutions

This paper studies how to inject external human knowledge to neural networks. It proposes a new Symbolic Graph Reasoning (SGR) layer. A SGR layer has three components: local-to-Semantic voting, graph reasoning, and semantic-to-local mapping. The proposed method shows improvement in segmentation and classification across multiple datasets: COCO-stuff, ADE20k, and PASCAL-Context and CIFAR-100. Authors proposed a new layer called (SGR).