AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Visual Distant Supervision for Scene Graph Generation

Yuan Yao, Ao Zhang, Xu Han, Mengdi Li, Cornelius Weber, Zhiyuan Liu, Stefan Wermter, Maosong Sun

ICCV 2021 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering · 38 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 denoising (DNS) plus external CLIP signal to distant supervision (ablation)Motif trained on distant labels · Visual Genome (20 predicates)PredCls R@50: 50.23 -> 53.40Improved
add external CLIP semantic signal to raw distant labels (ablation)Raw Label · Visual Genome (20 predicates)PredCls R@50: 30.61 -> 38.21Improved
train a scene graph model (Motif) on raw distant labels instead of using labels directly (ablation)Raw Label · Visual Genome (20 predicates)PredCls R@50: 30.61 -> 50.23Improved
use the external CLIP signal alone as predictor (ablation)EXT · Visual Genome (20 predicates)PredCls R@50: 6.64Hurt
add Cleanness Loss denoising baseline to distantly supervised Motif (ablation)Motif trained on distant labels · Visual Genome (20 predicates)PredCls R@50: 50.23 -> 51.10Improved
add Cleanness Loss denoising baseline to distantly supervised Motif (ablation)Motif trained on distant labels · Visual Genome (20 predicates)SGCls R@50: 24.90 -> 24.06Hurt
pre-train on distantly labeled data before fine-tuning on human labelsMotif (fully supervised) · Visual Genome (20 predicates)PredCls R@50: 67.93 -> 73.22Improved
add the denoising framework to semi-supervised pretraining (ablation)Motif + Pretrain · Visual Genome (20 predicates)PredCls R@50: 73.22 -> 76.28Improved
add the denoising framework to semi-supervised pretraining (ablation)Motif + Pretrain · Visual Genome (20 predicates)PredCls mR@50: 60.44 -> 60.20No clear effect
use distantly supervised model without human labels instead of weak supervisionWeak Supervision · Visual Genome (20 predicates)PredCls R@50: 44.96 -> 53.40Improved
swap general knowledge base for ideal knowledge base from Visual Genome annotationsMotif + DNS + EXT · Visual Genome (20 predicates, ideal KB)PredCls mR@50: 37.68 -> 50.87Improved
use semi-supervised distant supervision on the 50-predicate Visual Genome schemeMotif (fully supervised) · Visual Genome (50 predicates)PredCls R@50: 63.96 -> 64.43Improved

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