AI Paper Atlas

Research map / Detection and segmentation / CNN features

Specialize and Fuse: Pyramidal Output Representation for Semantic Segmentation

Chi-Wei Hsiao, Cheng Sun, Hwann-Tzong Chen, Min Sun

ICCV 2021 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 9 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 pyramidal output instead of single output (no contextual module) (ablation)segmentation head · ADE20K subset (HRNet32)mIoU: 40.42 -> 42.07Improved
add pyramidal output instead of single output (with ANL) (ablation)segmentation head · ADE20K subset (HRNet32)mIoU: 42.02 -> 43.07Improved
add pyramidal output instead of single output (with proposed contextual module) (ablation)segmentation head · ADE20K subset (HRNet32)mIoU: 42.00 -> 44.31Improved
add coarse-to-fine contextual module to single output (ablation)single-output baseline · ADE20K subset (HRNet32)mIoU: 40.42 -> 42.00Improved
add coarse-to-fine contextual module to pyramidal output (ablation)pyramidal output · ADE20K subset (HRNet32)mIoU: 42.07 -> 44.31Improved
add single ANL to pyramidal output (ablation)pyramidal output · ADE20K subset (HRNet32)mIoU: 42.07 -> 43.07Improved
add ANL at all pyramid levels (ANL-multi) (ablation)pyramidal output · ADE20K subset (HRNet32)mIoU: 42.07 -> 43.45Improved
train all levels on full map without relabeling (naive) (ablation)pyramidal output · ADE20K subset (HRNet32)mIoU: 40.42 -> 40.41No clear effect
relabel descendants of ground-truth unity-cells as don't care (ablation)pyramidal output · ADE20K subset (HRNet32)mIoU: 40.41 -> 41.54Improved
relabel descendants of true-positive unity-cells instead of ground truth (ablation)pyramidal output · ADE20K subset (HRNet32)mIoU: 41.54 -> 42.07Improved
use multi-level supervision as auxiliary only (no fuse) (ablation)single output + contextual module · ADE20K subset (HRNet32)mIoU: 42.00 -> 42.63Improved
use specialize and fuse rather than auxiliary supervision (ablation)single output + contextual module · ADE20K subset (HRNet32)mIoU: 42.63 -> 44.31Improved

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