深度过大会导致激光点云编码器隐藏状态崩溃，丧失分类能力。
Depth-Dependent Hidden-State Collapse in Dynamical System Autoencoders for LiDAR Point-Cloud Classification
- 通过控制编码器深度，发现深度为5时隐藏状态方差降至10^-5量级。
- 无论是否使用乘积系数，深度达5后三类分类器的宏F1均稳定在0.224688。
- 该现象揭示了动态系统自编码器在深结构下的实际失效风险，适合关注模型鲁棒性的研究者参考。
本文研究基于空间坐标与乘积系数特征增强的动态系统自编码器（DSAE）在激光点云分类中的应用。实验对比了编码器深度K=1至5的独立训练架构，并采用随机森林、kNN及多数类基线评估隐表示。主要发现：当深度K=5时，隐状态标准差降至10^-5量级，且三类分类器的宏F1分数均稳定在0.224688。理论证明类别间隐表示散度受总隐表示散度限制，而后者由隐状态方差主导，因此几乎恒定的隐表示无法保留有效类别区分结构。乘积系数在预崩溃阶段未提升宏F1，亦未能阻止深度为5时的崩溃。该结果明确指出大深度表示崩溃是当前DSAE点云分类的一个具体失败模式。
原文摘要 · Abstract (English)
We study Dynamical System Autoencoders (DSAE) for LiDAR point-cloud classification using spatial coordinates and Product Coefficient feature augmentations. The experiments compare separately trained DSAE architectures at encoder depths $K=1,\ldots,5$ and evaluate the resulting hidden representations with Random Forest, kNN, and a majority-class Dummy baseline. The main finding is a hidden-state collapse at $K=5$. For both xyz and xyz plus Product Coefficient inputs, the hidden-state standard deviation falls to the order of $10^{-5}$, while all three classifiers attain the same macro F1 score of $0.224688$. We prove that between-class hidden scatter is bounded by total hidden scatter, which in turn is controlled by the reported hidden-state variance. Thus a nearly constant hidden representation cannot retain substantial class-separating structure. Product Coefficients neither improve pre-collapse macro F1 nor prevent the $K=5$ collapse in the present DSAE setting. These results identify large-depth representation collapse as a concrete failure mode for DSAE LiDAR classification.
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。