AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Relationformer: A Unified Framework for Image-to-Graph Generation

Suprosanna Shit, Rajat Koner, Bastian Wittmann, Johannes Paetzold, Ivan Ezhov, Hongwei Li, Jiazhen Pan, Sahand Sharifzadeh, Georgios Kaissis, Volker Tresp, Bjoern Menze

ECCV 2022 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 86 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 the [rln]-token (linear relation head) (ablation)Relationformer · Visual Genome SGDetRecall@50: 22.0 -> 25.4Improved
add the [rln]-token (MLP relation head) (ablation)Relationformer · Visual Genome SGDetRecall@50: 26.4 -> 28.4Improved
add the [rln]-token (linear head) (ablation)Relationformer · Visual GenomeAP@50: 24.1 -> 25.3Improved
use an MLP instead of a linear relation head (with rln-token) (ablation)Relationformer · Visual Genome SGDetRecall@50: 25.4 -> 28.4Improved
add the [rln]-token (ablation)Relationformer · Synthetic vessel (3D)Node mAP: 75.5 -> 78.5Improved
add the [rln]-token (ablation)Relationformer · Synthetic vessel (3D)Edge mAP: 76.3 -> 78.1Improved
increase training data from 25% to 100% (ablation)Relationformer · Synthetic vessel (3D)Node mAP: 17.0 -> 78.5Improved
increase training data from 50% to 100% (ablation)Relationformer · Synthetic vessel (3D)Node mAP: 39.2 -> 78.5Improved
increase [obj]-tokens from 75 to 200 (ablation)Relationformer · Visual Genome SGDetRecall@50: 26.1 -> 28.4Improved
increase [obj]-tokens from 200 to 300 (ablation)Relationformer · Visual Genome SGDetRecall@50: 28.4 -> 27.9No clear effect
increase transformer layers from 4 to 6 (ablation)Relationformer · Visual Genome SGDetRecall@50: 26.5 -> 28.4Improved
add relation prediction on top of deformable DETR (MLP head, rln-token) (ablation)Relationformer · Visual GenomeAP@50: 26.4 -> 26.3No clear effect

Later papers that compared with this method

2 later accepted papers report Relationformer as a baseline in their results tables; 2 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 2 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