NuScenes-MQA: Integrated Evaluation of Captions and QA for Autonomous Driving Datasets using Markup Annotations
This work addresses the need for integrated evaluation of vision-language models in autonomous driving, though it is incremental as it builds on existing datasets and annotation methods.
The authors tackled the lack of QA-annotated datasets for autonomous driving by introducing Markup-QA, a novel annotation technique, and created the NuScenes-MQA dataset to enable simultaneous evaluation of sentence generation and VQA, with the dataset publicly available.
Visual Question Answering (VQA) is one of the most important tasks in autonomous driving, which requires accurate recognition and complex situation evaluations. However, datasets annotated in a QA format, which guarantees precise language generation and scene recognition from driving scenes, have not been established yet. In this work, we introduce Markup-QA, a novel dataset annotation technique in which QAs are enclosed within markups. This approach facilitates the simultaneous evaluation of a model's capabilities in sentence generation and VQA. Moreover, using this annotation methodology, we designed the NuScenes-MQA dataset. This dataset empowers the development of vision language models, especially for autonomous driving tasks, by focusing on both descriptive capabilities and precise QA. The dataset is available at https://github.com/turingmotors/NuScenes-MQA.