波段选择稳定性与语义分割性能：高光谱城市研究
Band-Selection Stability and Semantic Segmentation Performance: A Study on Hyperspectral City
- Valeo Vision Systems（法雷奥视觉系统公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究评估六种波段选择方法在高光谱城市数据上的稳定性与分割性能，发现方法内稳定性因方法而异，且与分割性能无一致关联，需多维度评估。
AI中文摘要：
资源约束使得高维高光谱成像在自主感知中具有挑战性，这促使使用波段选择方法。然而，波段选择方法对采样数据的敏感性及其与语义分割模型（SSM）的关系仍未得到充分探索。本研究在十个独立采样、类别平衡的兴趣区域（ROI）集上评估了六种波段选择方法，从Hyperspectral City V2（128个波段：450-950nm）数据集中产生了60个前25波段子集。来自前三个ROI集的前K个波段（K∈{3,5,...13}）使用三个SSM与相应的128波段基线进行评估。实验表明，方法内稳定性依赖于方法：Sim-LP显示出最高的稳定性（成对Jaccard相似度），并且与JMIM+CSNR一起产生了最佳分割结果。基于前K个波段的SSM与基线保持竞争力，在K=9时，mIoU和mF1分别提高了最多2.01和1.72个百分点，CPU推理速度提高了18-22倍。然而，性能并不随K单调增加，稳定性与SSM性能之间没有一致关联。这些发现表明，方法内稳定性具有信息性，但作为下游分割性能的指标并不可靠，强调需要在重复样本、子集大小和SSM上评估波段选择方法。
英文摘要：
Resource constraints make high-dimensional hyperspectral imaging challenging in autonomous perception, motivating the use of band selection methods. However, the sensitivity of band-selection methods to sampled data and their relationship to semantic segmentation models (SSMs) remain underexplored. This study evaluates six band selection methods on ten independently sampled, class-balanced region-of-interest (ROI) sets, yielding 60 top-25 band subsets from the Hyperspectral City V2 (128 bands: 450-950nm) dataset. Top-$K$ bands ($K\in\{3,5, ... 13\}$) from the first three ROI sets are evaluated with three SSMs against the corresponding 128-band baseline. Experiments show that intra-method stability is method-dependent: Sim-LP shows the highest stability (pairwise Jaccard similarity) and, together with JMIM+CSNR, yields the best segmentation results. Top-$K$ based SSMs remain competitive with baselines, with gains of up to 2.01 mIoU and 1.72 mF1 points, and 18-22x faster CPU inference for $K=9$. However, performance does not improve monotonically with $K$, and stability shows no consistent association with SSM performance. These findings suggest that intra-method stability is informative but an unreliable indicator of downstream segmentation performance, highlighting the need to evaluate band-selection methods across repeated samples, subset sizes, and SSMs.
