Semantic scene graph generation based on an edge dual scene graph and message passing neural network☆

Along with generative AI, interest in scene graph generation (SGG), which comprehensively captures the relationships and interactions between objects in an image and creates a structured graph-based representation, has significantly increased in recent years. However, relying on object-centric and dichotomous relationships, existing SGG methods have a limited ability to accurately predict detailed relationships. To solve these problems, a new approach to the modeling multi-object relationships, called edge dual scene graph generation (EdgeSGG), is proposed herein. EdgeSGG is based on an edge dual scene graph and object-relation centric message passing neural network (OR-MPNN), which can capture rich contextual interactions between unconstrained objects. To facilitate the learning of edge dual scene graphs with a symmetric graph structure, the proposed OR-MPNN learns both object-and relation-centric features for more accurately predicting relationaware contexts and allows fine-grained relational updates between objects. A comparative experiment with state-of-the-art (SoTA) methods was conducted using two public datasets for SGG operations and six metrics for three subtasks. Compared with SoTA approaches, the proposed model exhibited substantial performance improvements across all SGG subtasks. Furthermore, experiment on imbalanced class distributions revealed that incorporating the relationships between objects effectively mitigates existing long-tail problems. Our code is available at https://github.com/Chocolate-Love/EdgeSGG-pytorch.