AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Visibility Graphs for Image Processing

Jacopo Iacovacci, Lucas Lacasa

TPAMI 2019 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering

Read the paper

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
add local visibility patch features to global degree distribution (ablation)IVG+IHVG SVM · 2D HeLaaccuracy: 75.4% -> 83.5%Improved
add global degree distribution to local patch profiles (ablation)IVG+IHVG SVM · 2D HeLaaccuracy: 79.5% -> 83.5%Improved
add global and local multiplex features together (vs global only) (ablation)multiplex IVG+IHVG ova-qSVM · Usptexaccuracy: 93.6% -> 98.4%Improved
add global and local multiplex features together (vs local only) (ablation)multiplex IVG+IHVG ova-qSVM · Multibandaccuracy: 99.4% -> 99.6%Improved
add global and local multiplex features together (vs global only) (ablation)multiplex IVG+IHVG ova-qSVM · Brodatz Coloredaccuracy: 98.7% -> 99.8%Improved
use IHVG instead of IVG for global degree distributionP(k) features · 2D HeLamodel average accuracy: 57.2% -> 67.6%Improved
use IVG instead of IHVG for local patch profileZ features · 2D HeLamodel average accuracy: 74% -> 75.8%Improved
add PCA to IVG P(k) features (ablation)quadratic SVM / weighted KNN · Kylbergaccuracy: 94.2% -> 100%Mixed
use IHVG instead of IVG degree distributionComplex Tree · Kylbergaccuracy: 95.3% -> 100%Improved
apply k-filter degree cut-off at 24IHVG k-filter compressor · Lena 512x512file size: 50% size reductionImproved
use C-filter instead of k-filter at high compressionIHVG filters · LenaIC ratio IC_F(I)/IC_I: 0.2 at FCP=1.5 vs 0.5 at FCP=2 for k-filterHurt
use C-filter instead of k-filter with no compressionIHVG filters · LenaIC ratio IC_F(I)/IC_I: 0.97 at FCP=1Improved

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