arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.02541cs.CLcs.AIcs.CV
收藏

零样本基于知识的视觉问答的知识生成

Knowledge Generation for Zero-shot Knowledge-based VQA

School of Computing and Information Systems(计算与信息系统学院);Singapore Management University(新加坡管理大学)

Rui Cao, Jing Jiang

AI总结:

本文提出一种基于LLM生成知识的零样本K-VQA方法,先由LLM生成知识再整合用于问答,在两个基准上优于现有零样本方法,且生成知识相关有用。

摘要:

以往解决基于知识的视觉问答(K-VQA)的方法是从外部知识库检索知识,并使用监督学习来训练K-VQA模型。最近,预训练的大语言模型(LLM)被用作K-VQA的知识来源和零样本问答模型,并展示了有前景的结果。然而,这些近期方法没有明确展示回答问题所需的知识,因此缺乏可解释性。受近期从LLM生成知识用于基于文本的问答工作的启发,在本工作中,我们提出并测试了一种类似的基于知识生成的K-VQA方法,该方法首先从LLM生成知识,然后以零样本方式将生成的知识整合到K-VQA中。我们在两个K-VQA基准上评估了我们的方法,发现我们的方法优于之前的零样本K-VQA方法,并且我们生成的知识通常是相关且有用的。

英文摘要:

Previous solutions to knowledge-based visual question answering~(K-VQA) retrieve knowledge from external knowledge bases and use supervised learning to train the K-VQA model. Recently pre-trained LLMs have been used as both a knowledge source and a zero-shot QA model for K-VQA and demonstrated promising results. However, these recent methods do not explicitly show the knowledge needed to answer the questions and thus lack interpretability. Inspired by recent work on knowledge generation from LLMs for text-based QA, in this work we propose and test a similar knowledge-generation-based K-VQA method, which first generates knowledge from an LLM and then incorporates the generated knowledge for K-VQA in a zero-shot manner. We evaluate our method on two K-VQA benchmarks and found that our method performs better than previous zero-shot K-VQA methods and our generated knowledge is generally relevant and helpful.

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。

↑