AI Paper Atlas

Research map / Detection and segmentation / CNN features

Adaptive Context Network for Scene Parsing

Jun Fu, Jing Liu, Yuhang Wang, Yong Li, Yongjun Bao, Jinhui Tang, Hanqing Lu

ICCV 2019 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 150 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 global context module (gated by pixel-feature similarity) instead of plain global pooling sum (ablation)Res-50 dilated FCN (output 1/16) · Cityscapes valmIoU: 71.24 -> 72.45Improved
same, with output stride 1/8 (ablation)Res-50 dilated FCN (output 1/8) · Cityscapes valmIoU: 72.77 -> 74.50Improved
add global context module to baseline (ablation)Res-50 (output 1/16) · Cityscapes valmIoU: 69.15 -> 72.45Improved
set delta to 5 rather than 10 (ablation)Global context module · Cityscapes valmIoU: 71.87 -> 72.45Improved
set delta to 5 rather than 2 (ablation)Global context module · Cityscapes valmIoU: 72.36 -> 72.45No clear effect
add ungated local context from block-2 (ablation)Res-50+GCM · Cityscapes valmIoU: 72.45 -> 73.48Improved
gate local context with reversed global coefficient (LCM) (ablation)Res-50+GCM+LC · Cityscapes valmIoU: 73.48 -> 74.03Improved
reuse gated local features three times (ablation)Res-50+GCM+LCM(1) · Cityscapes valmIoU: 74.03 -> 74.67Improved
cascade three adaptive context blocks instead of one (ablation)Res-50+ACB · Cityscapes valmIoU: 74.67 -> 76.53Improved
use ResNet-101 with three blocks instead of ResNet-50 (ablation)ACB#3 · Cityscapes valmIoU: 76.53 -> 77.42Improved
add multi-grid dilated convolution (ablation)Res-101+ACB#3 · Cityscapes valmIoU: 77.42 -> 78.50Improved
add multi-scale data augmentation (ablation)Res-101+ACB#3+MG · Cityscapes valmIoU: 78.50 -> 80.09Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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