Metraipolis › archive › dc_ec78f6776d85
SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning — arXiv:2610.21087
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21087
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:06:57.825Z
- SHA-256 of the archived text
04c401ff0f00ba85a0e14f5cbab9329d2e1c7e4d8cc0fbb92c67d7ed20a85987- Stable URL of this page
https://metraipolis.com/documento/dc_ec78f6776d85
How to cite
SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning — arXiv:2610.21087 — arXiv (en), https://arxiv.org/abs/2610.21087 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec78f6776d85 (Metraipolis archive dc_ec78f6776d85, sha256 04c401ff0f00ba85a0e14f5cbab9329d2e1c7e4d8cc0fbb92c67d7ed20a85987)
BibTeX
@misc{dcec78f6776d85,
title = {SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning — arXiv:2610.21087},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21087},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec78f6776d85; sha256 04c401ff0f00ba85a0e14f5cbab9329d2e1c7e4d8cc0fbb92c67d7ed20a85987},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21087. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.21087 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T08:44:17.904Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).