AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Unbiased Heterogeneous Scene Graph Generation with Relation-Aware Message Passing Neural Network

Kanghoon Yoon, Kibum Kim, Jinyoung Moon, Chanyoung Park

AAAI 2023 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 40 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 heterogeneous relation-aware message passing instead of homogeneous BGNN message passingSGG models · Visual Genome PredClsmR@50/100: 30.4/32.9 -> 31.6/33.5Improved
use heterogeneous relation-aware message passing instead of homogeneous BGNN message passingSGG models · Visual Genome SGClsmR@50/100: 14.3/16.5 -> 17.2/18.7Improved
use heterogeneous relation-aware message passing instead of homogeneous BGNN message passingSGG models · Visual Genome SGGenmR@50/100: 10.7/12.6 -> 12.2/14.4Improved
use heterogeneous relation-aware message passing instead of BGNNSGG models · Open Images V6 SGGenmR@50: 40.5 -> 42.7Improved
use heterogeneous relation-aware message passing instead of BGNNSGG models · Open Images V6 SGGenR@50: 75.0 -> 76.8Improved
add relation-type-specific weights to the edge-wise update (ablation)HetSGG · Visual Genome SGClsmR@100: 15.9 -> 16.2Improved
add relation-type-specific weights to the node-wise update (ablation)HetSGG · Visual Genome SGClsmR@100: 15.9 -> 17.7Improved
add relation-type-specific weights to both edge-wise and node-wise updates (ablation)HetSGG · Visual Genome SGClsmR@100: 15.9 -> 18.7Improved
use 8 basis matrices rather than 4 (ablation)HetSGG · Visual Genome SGClsmR@100: 17.2 -> 18.7Improved
use 8 basis matrices rather than 12 (ablation)HetSGG · Visual Genome SGClsmR@100: 17.6 -> 18.7Improved
use 8 basis matrices rather than 16 (ablation)HetSGG · Visual Genome SGClsmR@100: 18.2 -> 18.7Improved
use ground-truth object types rather than inferred types (ablation)HetSGG with three object types · Visual Genome SGClsmR@50/100: 17.2 / 18.7 -> 17.4 / 19.1Improved

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