AI Paper Atlas

Research map / Point clouds / Point cloud classification

A Framework for Fast and Stable Representations of Multiparameter Persistent Homology Decompositions

David Loiseaux, Mathieu Carrière, Andrew Blumberg

NeurIPS 2023 · Point clouds › Point cloud classification · approach: Equivariant point cloud networks · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the proposed stable decomposition representation instead of the strongest listed baselineUCR classification · GPaccuracy: 94.0 -> 96.3Improved
Use the proposed stable decomposition representation instead of the strongest listed baselineUCR classification · IPDaccuracy: 95.5 -> 81.2Hurt
Use the proposed stable decomposition representation instead of the strongest listed baselineUCR classification · GPMVFaccuracy: 99.7 -> 95.3Hurt
Use the proposed stable decomposition representation instead of the strongest listed baselineUCR classification · GPASaccuracy: 96.5 -> 88.0Hurt
Use the proposed stable decomposition representation instead of the strongest listed baselineUCR classification · DPOAGaccuracy: 77.0 -> 71.9Hurt
Use the proposed stable decomposition representation instead of the strongest listed baselineUCR classification · PPOAGaccuracy: 82.0 -> 81.9No clear effect
Use the proposed stable decomposition representation instead of Ripley, P, or MPLImmunohistochemistry classification · Immunohistochemistryaccuracy: 67.2 ± 2.3 -> 91.4 ± 1.6; 60.7 ± 4.2 -> 91.4 ± 1.6; 65.3 ± 3.0 -> 91.4 ± 1.6Improved
Use the proposed representation rather than MPI (50) or MPL (50)Annulus and immunohistochemistry representation computation · Annulus and Immunohistochemistryruntime: 250ms± 2ms vs 6.43s± 25ms; 250ms± 2ms vs 17s± 39ms; 275 ms ± 9.8ms vs 5.67s ± 23.3ms; 275 ms ± 9.8ms vs 15.6s ± 14msImproved
Use stable representations of candidate decompositions rather than MPINoisy annulus convergence experiment · Noisy annulusconvergenceImproved
Choose stable representation parameters rather than the MPI representationMultiparameter persistence representation · Perturbations of decompositionsstabilityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy