分析3D形状检索中谱描述子的频率尺度重要性，发现短尺度主导性能。
Frequency-Scale Saliency for Spectral Descriptor Analysis in 3D Shape Retrieval
- 通过消融实验量化各频率尺度对检索的贡献
- 短尺度提升性能，长尺度反而有害，提升硬类别mAP 0.156
- 揭示不同类别间描述子相似性与失败的相关性
经典的谱描述子如热核签名（HKS）和波核签名（WKS）广泛用于非刚性3D形状检索，但其失效机制仍不清晰。本文提出频率-尺度显著性框架，通过消融分析量化每个尺度区间的检索贡献。引入类别谱指纹表征类别级尺度依赖关系，发现类别对间描述子相似性与检索失败高度相关，斯皮尔曼相关系数达0.479。在SHREC'11数据集上的实验表明：短尺度主导检索性能，长尺度有害；HKS与WKS表现出不同的尺度依赖模式；基于显著性加权的检索在困难类别上将mAP提升0.156，跨折和随机权重控制验证了该提升稳定且非偶然。
原文摘要 · Abstract (English)
Classical spectral descriptors such as the Heat Kernel Signature and Wave Kernel Signature are widely used for non-rigid 3D shape retrieval, yet their failure modes remain poorly understood. We present a frequency-scale saliency framework that audits these descriptors by quantifying the retrieval-level contribution of each descriptor scale interval through ablation. We introduce class spectral fingerprints to characterize category-level scale dependence, and show that descriptor similarity between class pairs is substantially correlated with retrieval failure, with a Spearman correlation of 0.479. Experiments on SHREC'11 demonstrate that short scales dominate retrieval performance while long scales are harmful, that HKS and WKS exhibit distinct scale dependence patterns, and that saliency-weighted retrieval improves mAP on hard categories by 0.156, with cross-fold and random-weight controls confirming that the gain is stable and not due to arbitrary reweighting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。