Metraipolis › archive › dc_a28db456a6ef

Do We Still Need Rotation-Invariant Architectures? A Statistical Robustness Benchmark for Point Cloud Classification — arXiv:2611.03952

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03952
License (as archived)
CC0-1.0
Archived
2026-11-04T12:41:23.960Z
SHA-256 of the archived text
56a9289f02ac29c94ff8dd77123e3a19afdf9491448c72ef59b605d103817510
Stable URL of this page
https://metraipolis.com/documento/dc_a28db456a6ef

How to cite

Do We Still Need Rotation-Invariant Architectures? A Statistical Robustness Benchmark for Point Cloud Classification — arXiv:2611.03952 — arXiv (en), https://arxiv.org/abs/2611.03952 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a28db456a6ef (Metraipolis archive dc_a28db456a6ef, sha256 56a9289f02ac29c94ff8dd77123e3a19afdf9491448c72ef59b605d103817510)
BibTeX
@misc{dca28db456a6ef,
  title = {Do We Still Need Rotation-Invariant Architectures? A Statistical Robustness Benchmark for Point Cloud Classification — arXiv:2611.03952},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03952},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a28db456a6ef; sha256 56a9289f02ac29c94ff8dd77123e3a19afdf9491448c72ef59b605d103817510},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03952. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A substantial line of work builds rotation invariance directly into point cloud architectures. We benchmark 10 architectures (PointNet, PointNet++, DGCNN, RIConv, RIConv++, RISurConv, PointMLP, PointTransformer, and the equivariant VN-PointNet and VN-DGCNN) across 5 domains under pose, noise, and occlusion, and analyze the results with confirmatory hypothesis tests rather than point estimates. The three rotation-invariant (RI) architectures achieve the best pose robustness but rank among the lowest on noise robustness in 4 of 5 domains. We ask whether this cost is intrinsic to invariance or specific to how invariance is obtained. We retrain all 10 architectures unchanged, with a simple invariance loss on the embedding and three training seeds each, and evaluate all models on the independently designed ModelNet40-C. Invariance training transfers narrowly but reliably. It improves exactly the corruption families its perturbations target wherever the baseline has headroom (mean occlusion +10.5, lidar +13.4 percentage points of accuracy). At matched training budget the best standard backbone and the best RI architecture end on par on unseen corruptions (within 2.5 percentage points in every seed), and invariance-trained RIConv++ is the most seed-stable top model. Once rotation augmentation is widened, standard backbones concede only a flat, angle-independent accuracy offset under full-sphere rotation. We release the benchmark along with a package for analyzing point cloud robustness and reproducing our results.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.03952 — 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 2026-11-04T12:29:47.373Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).