AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation

Yikang Li, Wanli Ouyang, Bolei Zhou, Jianping Shi, Chao Zhang, Xiaogang Wang

ECCV 2018 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 293 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 subgraph clustering instead of per-pair phrase features (64 boxes) (ablation)F-Net · VG-MSDNinference time (s/image): 0.65 -> 0.18Improved
use subgraph clustering instead of per-pair phrase features (64 boxes) (ablation)F-Net · VG-MSDNSGGen Rec@100: 10.81 -> 10.33Hurt
raise object proposals from 64 to 200 with subgraphs (ablation)F-Net · VG-MSDNSGGen Rec@100: 10.33 -> 12.02Improved
add 2-D feature map for subgraph features (ablation)F-Net · VG-MSDNSGGen Rec@50: 9.73 -> 9.90Improved
add one spatial-weighted message passing (SMP) structure (ablation)F-Net · VG-MSDNSGGen Rec@100: 12.08 -> 14.55Improved
add Spatial-sensitive Relation Inference (SRI) (ablation)F-Net · VG-MSDNSGGen Rec@100: 14.55 -> 16.12Improved
add Spatial-sensitive Relation Inference (SRI) (ablation)F-Net · VG-MSDNPhrDet Rec@50: 20.48 -> 22.54Improved
stack a second SMP module (1 -> 2) (ablation)F-Net · VG-MSDNSGGen Rec@100: 16.12 -> 16.47Improved
stack a second SMP module (1 -> 2) (ablation)F-Net · VG-MSDNinference time (s/image): 0.44 -> 0.55Hurt
compare F-Net 2-SMP against MSDNF-Net · VG-MSDNSGGen Rec@50: 10.72 -> 13.06Improved
compare F-Net 2-SMP against DR-NetF-Net · VG-DR-NetSGGen Rec@50: 20.79 -> 19.88Hurt
compare F-Net 2-SMP against DR-NetF-Net · VG-DR-NetPhrDet Rec@100: 27.57 -> 32.63Improved

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