Zero-shot Visual Question Answering using Knowledge Graph

TL;DR

This paper introduces a zero-shot visual question answering method leveraging knowledge graphs and a mask-based learning mechanism, effectively handling unseen answers and improving performance over existing models.

Contribution

It proposes a novel zero-shot VQA algorithm that integrates knowledge graphs with a mask-based learning approach, addressing answer bias and unseen answers issues.

Findings

Achieves state-of-the-art zero-shot VQA performance on unseen answers.

Significantly improves existing end-to-end models on the F-VQA dataset.

Introduces new answer-based zero-shot splits for the F-VQA dataset.

Abstract

Incorporating external knowledge to Visual Question Answering (VQA) has become a vital practical need. Existing methods mostly adopt pipeline approaches with different components for knowledge matching and extraction, feature learning, etc.However, such pipeline approaches suffer when some component does not perform well, which leads to error propagation and poor overall performance. Furthermore, the majority of existing approaches ignore the answer bias issue -- many answers may have never appeared during training (i.e., unseen answers) in real-word application. To bridge these gaps, in this paper, we propose a Zero-shot VQA algorithm using knowledge graphs and a mask-based learning mechanism for better incorporating external knowledge, and present new answer-based Zero-shot VQA splits for the F-VQA dataset. Experiments show that our method can achieve state-of-the-art performance in Zero-shot VQA with unseen answers, meanwhile dramatically augment existing end-to-end models on the normal F-VQA task.