AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation

Jaehyeong Jeon, Kibum Kim, Kanghoon Yoon, Chanyoung Park

ECCV 2024 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 14 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
apply DPL to MotifsMotifs · VG150 PredClsmR@50 / 100: 14.8 / 16.1 -> 33.7 / 37.4Improved
apply DPL to MotifsMotifs · VG150 PredClsR@50 / 100: 65.2 / 67.0 -> 54.4 / 56.3Hurt
apply DPL to Motifs on GQAMotifs · GQA200 PredClsmR@50 / 100: 14.9 / 15.6 -> 31.6 / 33.9Improved
use DPL instead of IETrans on VCTreeVCTree · VG150 PredClsF@50 / 100: 38.6 / 41.9 -> 42.7 / 45.1Improved
add unbiased inference with sigma-normalized distance (ablation)DPL · VG150 PredCls MotifsF@50 / 100: 27.2 / 29.4 -> 41.6 / 44.9Improved
add orthogonal loss when using unbiased inference (ablation)DPL · VG150 PredCls MotifsmR@50 / 100: 24.7 / 26.9 -> 33.7 / 37.4Improved
add orthogonal loss alone without matching loss or unbiased inference (ablation)DPL · VG150 PredCls MotifsF@50 / 100: 27.4 / 29.3 -> 26.6 / 28.5No clear effect
increase number of samples N from 1 to 40 (ablation)DPL · VG150 PredCls MotifsR@50: 40.6 -> 56.8Improved
increase number of samples N from 1 to 40 (ablation)DPL · VG150 PredCls MotifsmR@50: 36.4 -> 33.0Hurt
set matching radius R away from 1.0 (ablation)DPL · VG150 PredCls MotifsF@50: 41.6 -> 31.5 (R=0.6) / 31.4 (R=1.4)Hurt
assign more samples to head predicates than tail predicates (ablation)DPL · VG150 PredCls MotifsF@50 / 100: 37.7 / 40.5 -> 41.0 / 44.1Improved
reduce average N from 20 to 2 by setting N from predicate frequency (ablation)DPL · VG150 PredCls MotifsF@50 / 100: 41.3 / 44.6 -> 40.9 / 44.1No clear effect

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