Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledge

TL;DR

This paper proposes a hierarchical relation prediction and commonsense validation approach to improve scene graph generation, leading to more accurate and meaningful scene understanding results.

Contribution

It introduces a hierarchical relation head and a commonsense validation pipeline that enhance existing scene graph generation methods.

Findings

Significant improvement in scene graph accuracy on Visual Genome and OpenImage V6 datasets.

Effective integration of hierarchical relations and commonsense validation as plug-and-play modules.

Enhanced predictions include more reasonable and semantically consistent scene graphs.

Abstract

This work introduces an enhanced approach to generating scene graphs by incorporating both a relationship hierarchy and commonsense knowledge. Specifically, we begin by proposing a hierarchical relation head that exploits an informative hierarchical structure. It jointly predicts the relation super-category between object pairs in an image, along with detailed relations under each super-category. Following this, we implement a robust commonsense validation pipeline that harnesses foundation models to critique the results from the scene graph prediction system, removing nonsensical predicates even with a small language-only model. Extensive experiments on Visual Genome and OpenImage V6 datasets demonstrate that the proposed modules can be seamlessly integrated as plug-and-play enhancements to existing scene graph generation algorithms. The results show significant improvements with an extensive set of reasonable predictions beyond dataset annotations. Codes are available at https://github.com/bowen-upenn/scene_graph_commonsense.