GRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts

Lin Cheng; Zijiang Yang

GRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts

Computer Vision and Pattern Recognition 2020-11-12 v1

Authors: Lin Cheng , Zijiang Yang

Abstract

Program synthesis is the task to automatically generate programs based on user specification. In this paper, we present a framework that synthesizes programs from flow charts that serve as accurate and intuitive specifications. In order doing so, we propose a deep neural network called GRCNN that recognizes graph structure from its image. GRCNN is trained end-to-end, which can predict edge and node information of the flow chart simultaneously. Experiments show that the accuracy rate to synthesize a program is 66.4%, and the accuracy rates to recognize edge and nodes are 94.1% and 67.9%, respectively. On average, it takes about 60 milliseconds to synthesize a program.

Keywords

graph neural network graph convolutional network graph generation

Cite

@article{arxiv.2011.05980,
  title  = {GRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts},
  author = {Lin Cheng and Zijiang Yang},
  journal= {arXiv preprint arXiv:2011.05980},
  year   = {2020}
}

Related papers

View all related →