AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Fast Contextual Scene Graph Generation With Unbiased Context Augmentation

Tianlei Jin, Fangtai Guo, Qiwei Meng, Shiqiang Zhu, Xiangming Xi, Wen Wang, Zonghao Mu, Wei Song

CVPR 2023 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 24 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 context-only predictions with context augmentation instead of a visual-feature SGG approachC-SGG · VG PredCls and SGGenMean@K and F@K: 44.1/47.6 Mean@50/100 and 41.2/44.7 F@50/100; 20.8/23.8 Mean@50/100 and 19.0/21.9 F@50/100Improved
Add visual predicate analysis guided by contextual predictionsC-SGG · VG PredClsR@50/100: 55.2/59.2 -> 58.2/62.4Improved
Add visual predicate analysis guided by contextual predictionsC-SGG · VG SGGenmR@50/100: 14.8/17.1 -> 14.6/17.0No clear effect
Add visual predicate analysis guided by contextual predictionsC-SGG* · PSG SGGenR@20/100: 24.0/29.0 -> 25.3/29.8Improved
Add visual predicate analysis guided by contextual predictionsC-SGG* · PSG SGGenmR@20/100: 24.1/26.3 -> 23.0/25.8Hurt
Disable context augmentation (ε = 0) (ablation)C-SGG · VG PredClsmR@50/100: 32.9/36.0 -> 26.3/29.5Hurt
Set context augmentation factor to ε = 0.01 rather than ε = 0.05 (ablation)C-SGG · VG PredClsmR@50/100: 32.9/36.0 -> 27.8/30.2Hurt
Set context augmentation factor to ε = 0.1 rather than ε = 0.05 (ablation)C-SGG · VG PredClsMean@50/100: 44.1/47.6 -> 43.6/45.1Hurt
Use ReLuL1 loss rather than BCE loss (ablation)CV-SGG · VG PredClsmR@50/100: 23.1/26.4 -> 32.6/36.2Improved
Set ReLuL1 boost factor to η = 0.2 rather than η = 0.1 (ablation)CV-SGG · VG PredClsmR@50/100: 32.6/36.2 -> 27.7/30.1Hurt
Use context experience in addition to visual predictions (α = 0.1) (ablation)CV-SGG* · PSG SGGenmR@20/100: 12.6/13.1 -> 14.8/16.3Improved
Set context-vision weight to α = 0.5 rather than α = 0.7 (ablation)CV-SGG* · PSG SGGenmR@20/100: 23.0/25.8 -> 22.3/24.8Hurt

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