atlas

Research map / Graph learning / Graph algorithms and clustering

Universe Points Representation Learning for Partial Multi-Graph Matching

AAAI 2023 · Graph learning › Graph algorithms and clustering · approach: Deep learning for graph matching · 5 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 learned universe representations for object-to-universe matching (ablation)URL · Pascal VOCF1: 55.4±0.6 -> 71.7±0.5Helped
Add graph neural network processing with 2D and 3D SplineCNN blocks (ablation)URL · Pascal VOCF1: 55.1±0.6 -> 71.7±0.5Helped
Add 3DSplineCNN with a predicted virtual coordinate (ablation)URL with graph feature processing · Pascal VOCF1: 67.6±1.0 -> 71.7±0.5Helped
Use object-to-universe matching instead of pairwise matchingPascal VOC partial multi-graph matching · Pascal VOCF1: 61.4 -> 71.7Helped
Transfer the Pascal VOC-trained URL encoder without fine-tuning and use HiPPIWillow full matching · Willowaccuracy: 94.5 -> 98.9Helped
Use LAP rather than HiPPI with the transferred URL featuresURL on Willow · Willowaccuracy: 98.9 -> 95.0Hurt
Add URL universe representation learningpartial multi-graph matching · Pascal VOC and CUB-200-2011F1: 62.8 -> 71.7; 82.6 -> 95.1Helped

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