AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

RelTR: Relation Transformer for Scene Graph Generation

Yuren Cong, Michael Ying Yang, Bodo Rosenhahn

TPAMI 2023 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 275 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
add feature encoder layers (0 -> 6) (ablation)RelTR · Visual Genome SGDETR@50: 23.3 -> 27.5Improved
increase triplet decoder layers 3 -> 6 (ablation)RelTR · Visual Genome SGDETR@50: 25.9 -> 27.5Improved
increase triplet decoder layers 6 -> 9 (ablation)RelTR · Visual Genome SGDETR@50: 27.5 -> 27.1Hurt
increase encoder layers 6 -> 9 (ablation)RelTR · Visual Genome SGDETR@50: 27.5 -> 27.7No clear effect
add triplet decoder on top of entity decoder (ablation)RelTR · Visual Genome SGDETR@50: 18.3 -> 27.5Improved
add CSA to DVA-only decoder (ablation)RelTR · Visual Genome SGDETR@50: 20.9 -> 26.6Improved
add DEA to CSA+DVA decoder (ablation)RelTR · Visual Genome SGDETR@50: 26.6 -> 27.2Improved
add mask head for attention heat maps (ablation)RelTR · Visual Genome SGDETR@50: 27.2 -> 27.5No clear effect
use IoU-based assignment (threshold T<1) in set prediction loss (ablation)RelTR · Visual Genome SGDETR@50Improved
vary number of triplet queries N_t (ablation)RelTR · Visual Genome SGDETR@50Mixed
add bi-level resamplingRelTR · Visual Genome SGDETR@50 / mR@50: R@50 27.5 -> 24.1; mR@50 10.8 -> 13.9Mixed
add logit adjustmentRelTR · Visual Genome SGDETR@50 / mR@50: mR@50 10.8 -> 14.2; R@50 27.5 -> 25.9Mixed

Later papers that compared with this method

3 later accepted papers report RelTR as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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