AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Robo-SGG: Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene Graph Generation

Changsheng Lv, Zijian Fu, Mengshi Qi

CVPR 2026 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 1 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 Robo-SGG (NRM + LEE) to HiKERHiKER · VG-C SGClsmR@50: 3.5 -> 3.7Improved
add Robo-SGG to MOTIFSMOTIFS · VG clean SGDetmR@50: 7.2 -> 7.1No clear effect
add Robo-SGG to VTransEVTransE · VG clean SGClsmR@50: 12.6 -> 12.4Hurt
use NRM instead of SNR restitution (with LEE) (ablation)MOTIFS · VG-C PredClsmR@100: +2.2% -> +4.3%Improved
add LEE alone (ablation)HiKER · VG-C SGClsmR@50: 3.5 -> 3.5No clear effect
add NRM alone (ablation)MOTIFS · VG-C PredClsmR@50: 12.6 -> 12.8Improved
add both LEE and NRM (ablation)MOTIFS · VG-C PredClsmR@50: 12.6 -> 13.8Improved
fuse bbox embedding by concatenation instead of gating (ablation)VCTree LEE · VG-C SGDetmR@50: 2.51 -> 2.46Hurt
fuse bbox embedding by addition instead of gating (ablation)VCTree LEE · VG-C SGDetmR@50: 2.51 -> 2.48Hurt
add gate fusion in LEE (ablation)VCTree · VG-C SGDetmR@50: 2.51 -> 2.62Improved
use object centroids rather than bounding boxes in layout-aware attention (ablation)VCTree NRM · VG-C SGDetmR@50: 2.55 -> 2.69Improved
add Robo-SGG under increasing Gaussian noise severitybaseline SGG models · VG-C SGCls Gaussian noisemR@100: 4.6% (severity 1) -> 28.2% (severity 5) relative gainImproved

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