AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Graph Matching with Bi-level Noisy Correspondence

Yijie Lin, Mouxing Yang, Jun Yu, Peng Hu, Changqing Zhang, Xi Peng

ICCV 2023 · Graph learning › Graph algorithms and clustering · approach: Deep learning for graph matching · 48 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
add momentum distillation to the quadratic contrastive loss (ablation)COMMON · Pascal VOCmean matching accuracy (%): 81.77 -> 82.67Improved
add momentum distillation to the quadratic contrastive loss (ablation)COMMON · SPair-71kmean matching accuracy (%): 83.94 -> 84.54Improved
add within-graph and cross-graph consistency regularizers (ablation)COMMON · Pascal VOCmean matching accuracy (%): 81.95 -> 82.67Improved
add within-graph and cross-graph consistency regularizers (ablation)COMMON · SPair-71kmean matching accuracy (%): 83.83 -> 84.54Improved
use proposed quadratic loss instead of prior quadratic regularization with InfoNCE (ablation)COMMON · Pascal VOCmean matching accuracy (%): 81.67 -> 82.67Improved
add robust quadratic terms on top of plain InfoNCE (ablation)COMMON · SPair-71kmean matching accuracy (%): 83.38 -> 84.54Improved
vary distillation temperature alpha from 0.1 to 0.9 (ablation)COMMON · Pascal VOCmean matching accuracy (%): 82.34 -> 82.41 (range 82.34-82.69 for alpha 0.1-0.9)No clear effect
turn on distillation (alpha 0 -> 0.4) (ablation)COMMON · Pascal VOCmean matching accuracy (%): 81.90 -> 82.67Improved
apply COMMON to hard-viewpoint image pairsCOMMON · SPair-71k (hard viewpoint pairs)matching accuracy (%): 73.6 -> 76.4Improved
apply COMMON to easy-viewpoint image pairsCOMMON · SPair-71k (easy viewpoint pairs)matching accuracy (%): 86.5 -> 86.6No clear effect
add momentum distillation under synthetic keypoint noiseCOMMON · Willow Object synthetic noise 0-0.5matching accuracyImproved

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