Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting
This addresses the limitation of restricted expressiveness in visual knowledge extraction for AI systems, offering a novel approach that is not incremental.
The paper tackles the problem of extracting relational knowledge from images without pre-defined formats or vocabularies, presenting OpenVik, which uses a relation-oriented multimodality model to generate format-free knowledge, resulting in improved correctness and uniqueness in evaluations and consistent gains in visual reasoning applications.
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.