arXiv cs.AI· Jongann Lee, Sun Woo Park, Yun Young Choi·· 2 天前AI 评分22
SIEVE：解决等变自监督学习中的拓扑障碍
SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning
AI 导读
研究揭示 3D 点云掩码自编码与 SE(3) 等变网络存在理论不兼容，标准掩码会触发拓扑坍缩，迫使模型在无参考系下臆测朝向。为此提出 SIEVE（Scalar Invariant Extraction Via Equivariance）等变自监督框架，通过球形投影掩码保留全局姿态、遮蔽局部语义，将点云几何压缩为不变标量嵌入。
正文 · 原文
Abstract:We identify a theoretical incompatibility between 3D point cloud masked autoencoding and SE(3)-equivariant networks. We prove that standard masking triggers a topological collapse, effectively forcing the model to hallucinate orientation without a reference frame. To resolve this, we introduce SIEVE (Scalar Invariant Extraction Via Equivariance), an SE(3)-equivariant self-supervised framework that compresses point cloud geometry into invariant scalar embeddings. At its core is the spherical projection mask, which preserves global pose while obfuscating local semantics, sidestepping the obstruction by construction. Experiments confirm that SIEVE circumvents the predicted collapse where constant and noise masks fail. On downstream point cloud tasks, the resulting embeddings improve over coordinate-based baselines and hand-crafted geometric descriptors, with the largest gains on generalization to unseen shape categories.
| Comments: | The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS) 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Report number: | MPIM-Bonn-2026 |
| Cite as: | arXiv:2610.21087 [cs.LG] |
| (or arXiv:2610.21087v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21087 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jongann Lee [view email]
[v1]
Thu, 15 Oct 2026 01:42:50 UTC (9,739 KB)
来源：arXiv cs.AI · arxiv.org