Graph R-CNN for Scene Graph Generation

Authors:
  • JYJianwei Yang
    Jianwei Yang
  • JLJiasen Lu
    Jiasen Lu
  • SLStefan Lee
    Stefan Lee
  • DBDhruv Batra
    Dhruv Batra
  • DPDevi Parikh
    Devi Parikh
Preprint
Publisher website
Google Scholar
Abstract
We propose a novel scene graph generation model called Graph R-CNN, that is both effective and efficient at detecting objects and their relations in images. Our model contains a Relation Proposal Network (RePN) that efficiently deals with the quadratic number of potential relations between objects in an image. We also propose an attentional Graph Convolutional Network (aGCN) that effectively captures contextual information between objects and relations. Finally, we introduce a new evaluation metric that is more holistic and realistic than existing metrics. We report state-of-the-art performance on scene graph generation as evaluated using both existing and our proposed metrics.
All Related Versions