cs.CVJun 23, 2025

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

Authors: Imad Ali Shah, Jiarong Li, Tim Brophy, Martin Glavin, Edward Jones, Enda Ward, Brian Deegan

Organizations: School of Engineering, University of Galway, Ireland · Ryan Institute, University of Galway, Ireland · Valeo Vision Systems, Tuam, Ireland

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.

Figures & tables

Explore similar work

CardsList
  1. Challenges in Hyperspectral Imaging for Autonomous Driving: The HSI-Drive Case

    Mar 26, 2026Koldo Basterretxea, Jon Gutiérrez-Zaballa, Javier EchanobeHyperspectral ImagingAutonomous Driving Perception

  2. AD-SAM: Adapting the Segment Anything Model for Semantic Segmentation in Autonomous Driving

    Oct 30, 2025Het Patel, Mario Camarena, Fatemeh Nazari +3Vision Foundation Model AdaptationAutonomous Driving Perception

  3. Spectral Dynamic Attention Network for Hyperspectral Image Super-Resolution

    Apr 30, 2026Tengya Zhang, Feng Gao, Lin Qi +2Hyperspectral Image Super-ResolutionHyperspectral Imaging