Multi-Scale Spectral Attention Module-based Hyperspectral Segmentation in Autonomous Driving Scenarios

TL;DR

This paper investigates a Multi-Scale Attention Mechanism integrated into UNet to improve hyperspectral image segmentation for autonomous driving, demonstrating consistent performance gains across datasets.

Contribution

It introduces an empirical study of MSAM with adaptive multi-scale spectral feature extraction, showing its effectiveness over baseline methods in AD scenarios.

Findings

MSAM improves segmentation accuracy by 2.32% in mIoU.

Optimal kernel configurations are dataset-specific.

MSAM maintains competitive GPU performance.

Abstract

Recent advances in autonomous driving (AD) have highlighted the potential of hyperspectral imaging (HSI) for enhanced environmental perception, particularly in challenging weather and lighting conditions. However, efficiently processing high-dimensional spectral data remains a significant challenge. This paper presents an empirical investigation of a Multi-Scale Attention Mechanism (MSAM) for enhanced spectral feature extraction through three parallel 1D convolutions with varying kernel sizes (1-11) and adaptive feature aggregation. By integrating MSAM into UNet's skip connections, we evaluate performance improvements in semantic segmentation across multiple HSI datasets for urban driving scenarios. Comprehensive ablation studies demonstrate that MSAM consistently outperforms baseline UNet-SC, achieving average improvements of 2.32% in mIoU and 2.88% in mF1, while maintaining competitive GPU performance against established attention mechanisms. Our findings reveal that optimal kernel combinations are dataset-specific, with configurations such as (1;5;11) and (3;7;11) demonstrating particularly strong performance. This empirical investigation advances understanding of HSI processing capabilities for AD applications and establishes a foundation for adaptive multi-scale spectral feature extraction in automotive deployment.