Abstract
Hyperspectral sensing provides rich spectral information for scene understanding in urban driving, but its high dimensionality poses challenges for interpretation and efficient learning. We introduce Learnable Quantum Efficiency (LQE), a physics-inspired, interpretable dimensionality reduction (DR) method that parameterizes smooth high-order spectral response functions that emulate plausible sensor quantum efficiency curves. Unlike conventional methods or unconstrained learnable layers, LQE enforces physically motivated constraints, including a single dominant peak, smooth responses, and bounded bandwidth. This formulation yields a compact spectral representation that preserves discriminative information while remaining fully differentiable and end-to-end trainable within semantic segmentation models (SSMs). We conduct systematic evaluations across three publicly available multi-class hyperspectral urban driving datasets, comparing LQE against six conventional and seven learnable baseline DR methods across six SSMs. Averaged across all SSMs and configurations, LQE achieves the highest average mIoU, improving over conventional methods by 2.45\%, 0.45\%, and 1.04\%, and over learnable methods by 1.18\%, 1.56\%, and 0.81\% on HyKo, HSI-Drive, and Hyperspectral City, respectively. LQE maintains strong parameter efficiency (12--36 parameters compared to 51--22K for competing learnable approaches) and competitive inference latency. Ablation studies show that low-order configurations are optimal, while the learned spectral filters converge to dataset-intrinsic wavelength patterns. These results demonstrate that physics-informed spectral learning can improve both performance and interpretability, providing a principled bridge between hyperspectral perception and data-driven multispectral sensor design for automotive vision systems.
Abstract (translated)
高光谱感知为城市驾驶场景理解提供了丰富的光谱信息，但其高维度特性给解释和高效学习带来了挑战。我们提出了受物理启发的、可解释的降维方法——可学习量子效率（LQE），该方法通过参数化平滑的高阶光谱响应函数来模拟合理的传感器量子效率曲线。与传统方法或无约束的可学习层不同，LQE 强制执行物理动机约束，包括单一主导峰值、平滑响应和受限带宽。这种公式化产生了一种紧凑的光谱表示，在保留判别信息的同时，仍可在语义分割模型（SSMs）中实现完全可微和端到端训练。我们在三个公开可用的多类高光谱城市驾驶数据集上进行了系统评估，将 LQE 与六种传统方法和七种可学习基线降维方法在六个 SSMs 上进行了比较。平均所有 SSMs 和配置，LQE 实现了最高的平均 mIoU，在 HyKo、HSI-Drive 和 Hyperspectral City 数据集上分别比传统方法提升 2.45%、0.45% 和 1.04%，比可学习方法提升 1.18%、1.56% 和 0.81%。LQE 保持了强大的参数效率（12-36 个参数，而竞争的可学习方法为 51-22K）和具有竞争力的推理延迟。消融研究表明，低阶配置是最优的，而学习到的光谱滤波器收敛于数据集固有的波长模式。这些结果证明，物理信息光谱学习可以同时提升性能和可解释性，为高光谱感知与数据驱动的汽车视觉系统多光谱传感器设计之间架起了一座原则性的桥梁。
URL
https://arxiv.org/abs/2603.26528
