The Impact of Different Backbone Architecture on Autonomous Vehicle Dataset

TL;DR

This paper evaluates how different backbone architectures affect object detection performance across three autonomous vehicle datasets, highlighting the importance of architecture choice in autonomous driving contexts.

Contribution

It provides a comparative analysis of backbone architectures on autonomous vehicle datasets, an area previously unexplored.

Findings

Backbone architecture significantly influences detection accuracy in autonomous driving datasets.

Performance varies notably across datasets like KITTI, NuScenes, and BDD.

Certain architectures outperform others depending on the dataset and environment.

Abstract

Object detection is a crucial component of autonomous driving, and many detection applications have been developed to address this task. These applications often rely on backbone architectures, which extract representation features from inputs to perform the object detection task. The quality of the features extracted by the backbone architecture can have a significant impact on the overall detection performance. Many researchers have focused on developing new and improved backbone architectures to enhance the efficiency and accuracy of object detection applications. While these backbone architectures have shown state-of-the-art performance on generic object detection datasets like MS-COCO and PASCAL-VOC, evaluating their performance under an autonomous driving environment has not been previously explored. To address this, our study evaluates three well-known autonomous vehicle datasets, namely KITTI, NuScenes, and BDD, to compare the performance of different backbone architectures on object detection tasks.