atlas

Research map / Detection and segmentation / CNN features

Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation

CVPR 2018 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 146 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 dense decoder shortcut connections (ablation)Ours-101 · NYUDmean IoU: 46.3 -> 48.1Helped
Add context aggregation (convolution-pooling blocks) (ablation)Ours-101 · NYUDmean IoU: 46.4 -> 48.1Helped
Add dense decoder shortcut connections (ablation)RefineNet-101 · NYUDmean IoU: 43.6 -> 44.7Helped
Use the proposed ResNeXt-style modules and decoder rather than RefineNet-101Semantic segmentation on NYUD · NYUDmean IoU: 43.6 -> 48.1Helped
Use single-scale evaluation rather than multi-scale evaluationOurs · Pascal VOC 2012mean IoU: 82.6 -> 81.2Hurt
Use single-scale evaluation rather than multi-scale evaluationOurs · Pascal Person-Partmean IoU: 68.6 vs 68.6No 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