AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Dynamic Graph Generation Network: Generating Relational Knowledge From Diagrams

Daesik Kim, YoungJoon Yoo, Jee-Soo Kim, SangKuk Lee, Nojun Kwak

CVPR 2018 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 25 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 DGGN graph-structured message passing instead of a vanilla GRUDiagram relation inference · AI2D testmAP: 39.28 -> 44.08Improved
Use DGGN graph-structured message passing instead of a vanilla GRUDiagram relation inference · AI2D testIoU_edge: 15.58 -> 25.86Improved
Use diagram graph extraction in the QA pipeline instead of Dqa-Net(Dsdp)Dqa-Net · AI2Daccuracy: 38.47 -> 39.73Improved
Use diagram graph extraction in the QA pipeline instead of Dqa-Net(Dsdp)Dqa-Net · FOODWEBSaccuracy: 59.30 -> 58.22Hurt
Add the global diagram feature to DGGN (ablation)DGGN · AI2D testmAP: 39.34 -> 44.08Improved
Add the global diagram feature to DGGN (ablation)DGGN · AI2D testIoU_edge: 14.44 -> 25.86Improved
Add the global diagram feature to DGGN (ablation)DGGN · AI2D testIoU_node: 70.95 -> 69.77Hurt
Use edge-probability weights in the mean pool (ablation)DGGN · AI2D testmAP: 42.15 -> 44.08Improved
Use edge-probability weights in the mean pool (ablation)DGGN · AI2D testIoU_edge: 24.84 -> 25.86Improved
Add a 2 × 2 ROI-pooled feature to DGGN local features (ablation)DGGN · AI2D testmAP: 44.08 -> 39.73Hurt
Add a 2 × 2 ROI-pooled feature to DGGN local features (ablation)DGGN · AI2D testIoU_edge: 25.86 -> 23.00Hurt
Replace the graph generation branch with fully connected layersDiagram relation inference · AI2D testmAP: 44.08 -> 8.87Hurt

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