arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.05080cs.CVcs.LG
收藏

基于常识知识集成的Zero-Shot场景图关系预测

Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration

Emory University(埃默里大学)

Xuan Kan, Hejie Cui, Carl Yang

摘要:

图像中实体之间的关系预测是场景图生成的重要步骤,它进一步影响各种视觉理解和推理任务。然而,现有的SGG框架需要大量的训练,但不能对看不见的(即,zero-shot)三胞胎。在这项工作中,我们强调,这种无能是由于缺乏常识推理,即,基于对世界的一般理解,将类似实体关联起来并推断出类似关系的能力。为了填补这一空白,我们提出了Commonsense集成sCenegraphHrElation pRediction(COACHER),一个框架,以整合常识知识的SGG,特别是zero-shot关系预测。具体来说,我们开发了新的图形挖掘管道来模拟外部常识知识图谱中实体周围的邻域和路径,并将它们集成到最先进的SGG框架之上。对Visual Genome的原始数据集和操作数据集进行了广泛的定量评估和定性案例研究,证明了我们所提出的方法的有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑