AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Panoptic Scene Graph Generation

Jingkang Yang, Yi Zhe Ang, Zujin Guo, Kaiyang Zhou, Wayne Zhang, Ziwei Liu

ECCV 2022 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 146 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
train 60 epochs instead of 12PSGTR (ResNet-50) · PSG dataset, scene graph generation (SGDet)R@100: 4.27 -> 36.3Improved
train 60 epochs instead of 12PSGTR (ResNet-101) · PSG dataset, scene graph generation (SGDet)R@100: 4.00 -> 35.3Improved
train 60 epochs instead of 12PSGFormer (ResNet-50) · PSG dataset, scene graph generation (SGDet)R@100: 20.2 -> 20.1No clear effect
train 60 epochs instead of 12PSGFormer (ResNet-50) · PSG dataset, scene graph generation (SGDet)mR@100: 18.7 -> 17.6Hurt
model objects and relations with separate decoders and prompting-like matching (PSGFormer vs PSGTR)PSGTR (12 epochs, ResNet-50) · PSG dataset, scene graph generation (SGDet)mR@100: 1.57 -> 18.7Improved
replace VCTree with PSGFormer under 12 epochsVCTree (ResNet-101) · PSG dataset, scene graph generation (SGDet)mR@100: 10.3 -> 19.8Improved
replace VCTree with PSGFormer under 12 epochsVCTree (ResNet-101) · PSG dataset, scene graph generation (SGDet)R@100: 23.7 -> 21.0No clear effect
use GPSNet (explicit predicate direction) instead of MOTIFSMOTIFS (ResNet-50) · PSG dataset, scene graph generation (SGDet)R@100: 22.0 -> 20.1Hurt
use VCTree instead of MOTIFSMOTIFS (ResNet-50) · PSG dataset, scene graph generation (SGDet)R@100: 22.0 -> 22.5Improved
provide ground-truth segmentation (PredCls instead of SGDet)IMP (ResNet-50) · PSG dataset, R@20R@20: 16.5 -> 31.9Improved
use ResNet-101 instead of ResNet-50VCTree · PSG dataset, scene graph generation (SGDet)R@100: 22.5 -> 23.7Improved
use ResNet-101 instead of ResNet-50PSGTR (12 epochs) · PSG dataset, scene graph generation (SGDet)R@100: 4.27 -> 4.00No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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