面向可解释图基视觉问答的内在子图生成
Intrinsic Subgraph Generation for Interpretable Graph based Visual Question Answering
AI总结：
本文提出一种内在可解释的图基视觉问答方法，在GQA数据集上实现竞争性能，通过问答过程中生成解释性子图并提供自动评估指标，弥合可解释性与性能之间的差距。
摘要：
基于深度学习的方法在视觉问答（VQA）中的巨大成功同时增加了对可解释方法的需求。可解释人工智能（XAI）中的大多数方法侧重于生成事后解释，而非采用内在方法，后者以可解释模型为特征。在这项工作中，我们引入了一种用于图基VQA的可解释方法，并在GQA数据集上展示了具有竞争力的性能。该方法弥合了可解释性与性能之间的差距。我们的模型被设计为在问答过程中内在生成一个子图作为其解释，从而提供对决策过程的洞察。为了评估这些生成的子图的质量，我们将它们与已建立的图神经网络事后可解释性方法进行比较，并进行了人工评估。此外，我们提出了与人类评估者评价相关的定量指标，作为所生成解释性子图的自动评估指标。我们的实现可在 https://github.com/DigitalPhonetics/Intrinsic-Subgraph-Generation-for-VQA 获取。
英文摘要：
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 is designed to intrinsically produce a subgraph during the question-answering process as its explanation, providing insight into the decision making. To evaluate the quality of these generated subgraphs, we compare them against established post-hoc explainability methods for graph neural networks, and perform a human evaluation. Moreover, we present quantitative metrics that correlate with the evaluations of human assessors, acting as automatic metrics for the generated explanatory subgraphs. Our implementation is available at https://github.com/DigitalPhonetics/Intrinsic-Subgraph-Generation-for-VQA.
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。
