AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Learning Representations of Persistence Barcodes

Christoph D. Hofer, Roland Kwitt, Marc Niethammer

JMLR 2019 · Graph learning › Graph self-supervised learning · approach: Brain and biological graph learning · 49 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
learn the structure element parameters instead of only k-means++ initialization (frozen) (ablation)persistence barcode input layer · MPEG-7accuracy (%): 92.2 -> 92.7Improved
learn the structure element parameters instead of frozen k-means++ initialization (ablation)persistence barcode input layer · Animalaccuracy (%): 72.9 -> 74.6Improved
learn the structure element parameters instead of frozen k-means++ initialization (ablation)persistence barcode input layer · SHREC14 (Real)accuracy (%): 70.5 -> 72.2Improved
k-means++ initialization instead of random initialization of structure elements (ablation)input layer · MPEG-7accuracy (%)Improved
learning the parametrization instead of freezing it (ablation)input layer · MPEG-7 (varying N)accuracy (%)Improved
persistence images fed to a CNN instead of a linear SVMpersistence images · MPEG-7accuracy (%): 85.1 -> 92.3Improved
persistence images fed to a CNN instead of a linear SVMpersistence images · Animalaccuracy (%): 61.1 -> 69.4Improved
proposed learned layer instead of PSS kernelOurs (learned) · MPEG-7accuracy (%): 94.5 vs 92.7Hurt
proposed learned layer instead of PSS kernelOurs (learned) · Animalaccuracy (%): 73.6 -> 74.6Improved
proposed learned layer instead of persistence images with NNOurs (learned) · SHREC14 (Real)accuracy (%): 69.0 -> 72.2Improved
adding more convolution layers to persistence-image CNN (ablation)persistence images NN · benchmarksaccuracy (%)No clear effect
different initializations of r within a reasonable range (ablation)Ours · benchmarksaccuracy (%)No clear effect

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