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 2307.09329cs.CV
收藏

面向自动驾驶的预训练视觉问答模型性能分析探讨

Towards a performance analysis on pre-trained Visual Question Answering models for autonomous driving

University of Limerick(利默里克大学);Valeo Vision Systems(法雷奥视觉系统公司)

Kaavya Rekanar, Ciarán Eising, Ganesh Sistu, Martin Hayes

AI总结:

本文初步评估了ViLBERT、ViLT和LXMERT三种VQA模型在驾驶场景中的表现,发现结合跨模态注意力和后期融合技术的模型更具潜力,为后续九模型对比研究奠定基础。

摘要:

本文初步分析了三种流行的视觉问答(VQA)模型,即ViLBERT、ViLT和LXMERT,在回答与驾驶场景相关问题时的表现。通过比较模型回答与计算机视觉专家提供的参考答案的相似度,对这些模型的性能进行了评估。模型选择基于对多模态架构中transformer利用的分析。结果表明,结合跨模态注意力和后期融合技术的模型,在从驾驶视角生成更优答案方面展现出可喜的潜力。这一初步分析为即将进行的涉及九个VQA模型的全面比较研究奠定了基础,并为进一步研究自动驾驶场景中VQA模型查询的有效性做好了准备。补充材料可在https://github.com/KaavyaRekanar/Towards-a-performance-analysis-on-pre-trained-VQA-models-for-autonomous-driving获取。

英文摘要:

This short paper presents a preliminary analysis of three popular Visual Question Answering (VQA) models, namely ViLBERT, ViLT, and LXMERT, in the context of answering questions relating to driving scenarios. The performance of these models is evaluated by comparing the similarity of responses to reference answers provided by computer vision experts. Model selection is predicated on the analysis of transformer utilization in multimodal architectures. The results indicate that models incorporating cross-modal attention and late fusion techniques exhibit promising potential for generating improved answers within a driving perspective. This initial analysis serves as a launchpad for a forthcoming comprehensive comparative study involving nine VQA models and sets the scene for further investigations into the effectiveness of VQA model queries in self-driving scenarios. Supplementary material is available at https://github.com/KaavyaRekanar/Towards-a-performance-analysis-on-pre-trained-VQA-models-for-autonomous-driving.

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。

↑