AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

RU-Net: Regularized Unrolling Network for Scene Graph Generation

Xin Lin, Changxing Ding, Jing Zhang, Yibing Zhan, Dacheng Tao

CVPR 2022 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 48 citations (OpenAlex)

Check 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 U-MP to baseline GMP without GDE (ablation)RU-Net · VG SGCLSR@100: 41.2 -> 43.1Improved
Add GDE to baseline GMP without U-MP (ablation)RU-Net · VG PREDCLSR@100: 67.8 -> 69.2Improved
Add both U-MP and GDE instead of using neither module (ablation)RU-Net · VG SGCLSR@100: 41.2 -> 43.3Improved
Add both U-MP and GDE instead of using neither module (ablation)RU-Net · VG PREDCLSR@100: 67.8 -> 69.6Improved
Set graph regularization p to 0.1 rather than p=2 (ablation)RU-Net U-MP · VG SGCLSR@100: 41.9 -> 43.3Improved
Increase U-MP layers from 2 to 5 (ablation)RU-Net U-MP · VG SGCLSR@100: 42.7 -> 43.3Improved
Set GDE weight τ to 0.1 rather than 0.2 (ablation)RU-Net GDE · VG PREDCLSR@100: 68.3 -> 69.6Improved
Group relationship predictions by object categories and remove groups with fewer than three elements, rather than regularizing predictions per image (ablation)RU-Net GDE · VG PREDCLSmR@100: 22.5 -> 24.2Improved
Use RU-Net instead of R-CAGCN◇VG PREDCLS · VGmR@100: 19.9 -> 24.7Improved
Use RU-Net instead of RelDNOI V4 · OI V4score_wtd: 44.6 -> 48.2Improved
Use RU-Net instead of RelDNOI V6 · OI V6score_wtd: 40.8 -> 43.5Improved
Use RU-Net instead of Seq2Seq-RLVRD · VRD relation detectionR@50: 26.1 -> 27.4Improved

Later papers that compared with this method

1 later accepted paper reports RU-Net as a baseline in their results tables; 0 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 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