Intrinsic Subgraph Generation for Interpretable Graph based Visual Question Answering

arXiv:2403.17647v1 Announce Type: new
Abstract: The large success of deep learning based methods in Visual Question Answering (VQA) has concurrently increased the demand for explainable methods. Most methods in Explainable Artificial Intelligence (XAI) focus on generating post-hoc explanations rather than taking an intrinsic approach, the latter characterizing an interpretable model. In this work, we introduce an interpretable approach for graph-based VQA and demonstrate competitive performance on the GQA dataset. This approach bridges the gap between interpretability and performance. Our model …

arxiv cs.cl graph intrinsic question question answering type visual