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

TL;DR

This paper provides an initial performance analysis of three pre-trained VQA models in autonomous driving scenarios, focusing on their response similarity to expert answers and the impact of multimodal architecture features.

Contribution

It introduces a preliminary evaluation of ViLBERT, ViLT, and LXMERT models for driving-related VQA tasks, highlighting the influence of cross-modal attention and fusion techniques.

Findings

Models with cross-modal attention perform better.

Late fusion techniques show promising results.

Analysis sets the stage for comprehensive future studies.

Abstract

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.