AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Robust Multi-Object Matching via Iterative Reweighting of the Graph Connection Laplacian

Yunpeng Shi, Shaohan Li, Gilad Lerman

NeurIPS 2020 · Graph learning › Graph algorithms and clustering · approach: Optimization algorithms for graph matching · 5 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 IRGCL-P instead of PPMPermutation synchronization · Willow Carrelative estimation error: 0.11 -> 0.091Improved
Use IRGCL-S instead of IRLSPermutation synchronization · Willow Duckrelative estimation error: 0.19 -> 0.19No clear effect
Use IRGCL-S instead of IRLSPermutation synchronization · Willow Facerelative estimation error: 0.042 -> 0.039Improved
Use IRGCL-P instead of PPMPermutation synchronization · Willow Motorbikerelative estimation error: 0.44 -> 0.33Improved
Use IRGCL-P instead of MALSPermutation synchronization · Willow Winebottlerelative estimation error: 0.22 -> 0.21Improved
Use power iterations instead of spectral WLS (ablation)IRGCL · Willow datasetsrelative estimation error: Car: 0.14 -> 0.091; Duck: 0.19 -> 0.21; Face: 0.039 -> 0.051; Motorbike: 0.42 -> 0.33; Winebottle: 0.22 -> 0.21Mixed
Use the initial estimate without iterative reweighting (ablation)IRGCL · Willow datasetsrelative estimation error: Car: 0.14 -> 0.091; Duck: 0.19 -> 0.19; Face: 0.039 -> 0.039; Motorbike: 0.41 -> 0.33; Winebottle: 0.22 -> 0.21Mixed
Use IRGCL-S and IRGCL-P rather than least-squares baselinesPermutation synchronization · Local Biased and Local Adversarial corruption modelsmatching errorImproved
Use standard IRLS-Cauchy reweighting instead of IRGCLPermutation synchronization · Willow datasetsrelative estimation errorHurt

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