AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Representative Graph Neural Network

Changqian Yu, Yifan Liu, Changxin Gao, Chunhua Shen, Nong Sang

ECCV 2020 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 40 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
replace non-local block with RepGraph layer (S=9)R50 baseline · ADE20K val (ablation, R50)mIoU: 40.97 -> 43.12Improved
use a single representative node per position (S=1) (ablation)RepGraph layer · ADE20K val (ablation, R50)mIoU: 36.48 -> 42.53Improved
increase representative nodes from 9 to 27 (ablation)RepGraph layer · ADE20K val (ablation, R50)mIoU: 43.12 -> 43.06No clear effect
use bottleneck RepGraph instead of simple RepGraph (concat) (ablation)RepGraph layer · ADE20K val (instantiation, R50)mIoU: 42.98 -> 43.12Improved
use concatenation instead of summation fusion (ablation)Bottleneck RepGraph · ADE20K val (instantiation, R50)mIoU: 42.67 -> 43.12Improved
use concatenation instead of summation fusion (ablation)Non-local · ADE20K val (instantiation, R50)mIoU: 40.3 -> 40.97Improved
insert RepGraph layer at res3 vs res2/res4/res5 (ablation)Bottleneck RepGraph · ADE20K val (insertion stage, R50)mIoU: 41.25 -> 41.59No clear effect
add RepGraph layers (1 to 3 layers) (ablation)Bottleneck RepGraph · ADE20K val (number of layers, R50)mIoU: 41.59 -> 41.86Improved
add RepGraph layers (3 to 5 layers) (ablation)Bottleneck RepGraph · ADE20K val (number of layers, R50)mIoU: 41.86 -> 41.76No clear effect
group pixels spatially into nodes (Grid RepGraph g_s=65) (ablation)RepGraph layer · ADE20K val (Grid RepGraph, R50)mIoU: 43.12 -> 41.23Hurt
group channels (Group RepGraph g_c=32) (ablation)RepGraph layer · ADE20K val (Group RepGraph, R50)mIoU: 43.12 -> 42.38Hurt
group channels (g_c=8) (ablation)RepGraph layer · ADE20K val (Group RepGraph, R50)mIoU: 43.12 -> 43.01No 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