Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting

TL;DR

This paper introduces OpenVik, a novel open visual knowledge extraction framework that detects relational regions and generates format-free knowledge using multimodal prompting, enhancing knowledge diversity and reasoning performance.

Contribution

The work pioneers open visual knowledge extraction by combining relational region detection with multimodal prompting to produce diverse, format-free knowledge representations.

Findings

OpenVik effectively extracts correct and unique open visual knowledge.

The extracted knowledge improves visual reasoning tasks.

Data enhancement techniques increase knowledge diversity.

Abstract

Images contain rich relational knowledge that can help machines understand the world. Existing methods on visual knowledge extraction often rely on the pre-defined format (e.g., sub-verb-obj tuples) or vocabulary (e.g., relation types), restricting the expressiveness of the extracted knowledge. In this work, we take a first exploration to a new paradigm of open visual knowledge extraction. To achieve this, we present OpenVik which consists of an open relational region detector to detect regions potentially containing relational knowledge and a visual knowledge generator that generates format-free knowledge by prompting the large multimodality model with the detected region of interest. We also explore two data enhancement techniques for diversifying the generated format-free visual knowledge. Extensive knowledge quality evaluations highlight the correctness and uniqueness of the extracted open visual knowledge by OpenVik. Moreover, integrating our extracted knowledge across various visual reasoning applications shows consistent improvements, indicating the real-world applicability of OpenVik.