HSDA: High-frequency Shuffle Data Augmentation for Bird's-Eye-View Map Segmentation

TL;DR

This paper introduces HSDA, a novel high-frequency shuffle data augmentation technique in the frequency domain, significantly improving BEV map segmentation accuracy for autonomous driving by emphasizing high-frequency image details.

Contribution

The paper proposes HSDA, a new frequency domain augmentation method that enhances segmentation networks' ability to interpret high-frequency image content, leading to state-of-the-art results.

Findings

Achieved a new state-of-the-art mIoU of 61.3% on nuScenes.

Improved segmentation of small and intricate image regions.

Enhanced edge and detail perception in BEV map segmentation.

Abstract

Autonomous driving has garnered significant attention in recent research, and Bird's-Eye-View (BEV) map segmentation plays a vital role in the field, providing the basis for safe and reliable operation. While data augmentation is a commonly used technique for improving BEV map segmentation networks, existing approaches predominantly focus on manipulating spatial domain representations. In this work, we investigate the potential of frequency domain data augmentation for camera-based BEV map segmentation. We observe that high-frequency information in camera images is particularly crucial for accurate segmentation. Based on this insight, we propose High-frequency Shuffle Data Augmentation (HSDA), a novel data augmentation strategy that enhances a network's ability to interpret high-frequency image content. This approach encourages the network to distinguish relevant high-frequency information from noise, leading to improved segmentation results for small and intricate image regions, as well as sharper edge and detail perception. Evaluated on the nuScenes dataset, our method demonstrates broad applicability across various BEV map segmentation networks, achieving a new state-of-the-art mean Intersection over Union (mIoU) of 61.3% for camera-only systems. This significant improvement underscores the potential of frequency domain data augmentation for advancing the field of autonomous driving perception. Code has been released: https://github.com/Zarhult/HSDA