AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Learning Combinatorial Embedding Networks for Deep Graph Matching

Runzhong Wang, Junchi Yan, Xiaokang Yang

ICCV 2019 · Graph learning › Graph algorithms and clustering · approach: Deep learning for graph matching · 244 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
replace offset loss with permutation loss (ablation)GMN · Pascal VOC Keypointmatching accuracy (%): 55.3 -> 57.9Improved
use permutation loss instead of offset loss (ablation)PIA-GM · Pascal VOC Keypointmatching accuracy (%): 61.6 -> 63.0Improved
add cross-graph embedding on top of intra-graph (PCA-GM vs PIA-GM)PIA-GM · Pascal VOC Keypointmatching accuracy (%): 63.0 -> 63.8Improved
add cross-graph embedding (ablation)PCA-GM · Pascal VOC Keypoint (ablation)matching accuracy (%): 62.1 -> 63.6Improved
add learnable affinity metric (ablation)PCA-GM · Pascal VOC Keypoint (ablation)matching accuracy (%): 63.6 -> 63.8Improved
add intra-graph embedding (ablation)PCA-GM · Pascal VOC Keypoint (ablation)matching accuracy (%): 54.8 -> 62.1Improved
fine-tune VGG16 features on graph matching data (ablation)PCA-GM · Pascal VOC Keypoint (ablation)matching accuracy (%): 41.9 -> 54.8Improved
predict S iteratively in cross-graph module (7 iterations) instead of from shallow layer (ablation)PCA-GM · Pascal VOC Keypointmatching accuracy (%): 63.8 -> 46.2Hurt
predict S iteratively with 1 iteration instead of simple design (ablation)PCA-GM · Pascal VOC Keypointmatching accuracy (%): 63.8 -> 63.1Hurt
fine-tune on Willow after VOC pretrainingPCA-GM · Willow ObjectClass (duck)matching accuracy (%): 82.4 -> 93.5Improved
use PCA-GM instead of GMNPCA-GM-VOC · Willow ObjectClass (wine bottle)matching accuracy (%): 70.5 -> 95.1Improved
use PCA-GM instead of GMN (motorbike, Willow-trained)PCA-GM-Willow · Willow ObjectClass (motorbike)matching accuracy (%): 71.4 -> 76.7Improved

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