Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration

TL;DR

This paper introduces COACHER, a framework that integrates commonsense knowledge into scene graph generation to improve zero-shot relation prediction, addressing the limitations of existing models that require heavy training and cannot handle unseen triplets.

Contribution

The paper presents a novel method to incorporate external commonsense knowledge into SGG frameworks, enhancing zero-shot relation prediction capabilities.

Findings

COACHER outperforms baseline models on Visual Genome datasets.

The approach effectively models entity neighborhoods and paths in a knowledge graph.

Qualitative analysis shows improved reasoning for unseen triplets.

Abstract

Relation prediction among entities in images is an important step in scene graph generation (SGG), which further impacts various visual understanding and reasoning tasks. Existing SGG frameworks, however, require heavy training yet are incapable of modeling unseen (i.e.,zero-shot) triplets. In this work, we stress that such incapability is due to the lack of commonsense reasoning,i.e., the ability to associate similar entities and infer similar relations based on general understanding of the world. To fill this gap, we propose CommOnsense-integrAted sCenegrapHrElation pRediction (COACHER), a framework to integrate commonsense knowledge for SGG, especially for zero-shot relation prediction. Specifically, we develop novel graph mining pipelines to model the neighborhoods and paths around entities in an external commonsense knowledge graph, and integrate them on top of state-of-the-art SGG frameworks. Extensive quantitative evaluations and qualitative case studies on both original and manipulated datasets from Visual Genome demonstrate the effectiveness of our proposed approach.