AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

A Fair Ranking and New Model for Panoptic Scene Graph Generation

Julian Lorenz, Alexander Pest, Daniel Kienzle, Katja Ludwig, Rainer Lienhart

ECCV 2024 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 5 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
evaluate one-stage PSGG methods under fair SingleMPO instead of MultiMPOPSGTR, PSGFormer, Pair-Net, HiLo · PSG SGGenmR@50: HiLo 37.60 -> 18.33Hurt
replace first-stage model with MaskDINO for two-stage methodsVCTree, GPS-Net · PSG SGGenmR@50: +7.4 for VCTree, almost doubles GPS-NetImproved
add semantic token (with real masks) (ablation)DSFormer · PSG PredClsmR@50: 34.35 -> 36.64 (rectangular to masks plus semantic)Improved
add location token (with real masks) (ablation)DSFormer · PSG PredClsmR@50: 36.64 -> 40.06 with both tokens; 32.48 -> 38.78 without semantic token vs without locationImproved
add location token with rectangular masks (ablation)DSFormer · PSG PredClsmR@50: 33.75 -> 33.83No clear effect
add auxiliary node loss (weight 0.2) (ablation)DSFormer · PSG PredClsmR@50: 35.96 -> 40.06Improved
raise node loss weight from 0.2 to 0.5 (ablation)DSFormer · PSG PredClsmR@50: 40.06 -> 39.90No clear effect
increase transformer embedding dimension 192 to 384 (ablation)DSFormer · PSG PredClsmR@50: 38.01 -> 40.06Improved
use binary instead of ratio subject-object encoding (ablation)DSFormer · PSGmR@50No clear effect
use segmentation model with higher PQ as first stage for DSFormer (ablation)DSFormer · PSG SGGenmR@50: 26.97 (Mask2Former) -> 30.67 (MaskDINO)Improved

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