AI Paper Atlas

Research map / Detection and segmentation / CNN features

Pixel Consensus Voting for Panoptic Segmentation

Haochen Wang, Ruotian Luo, Michael Maire, Greg Shakhnarovich

CVPR 2020 · Detection and segmentation › CNN features · approach: Unified panoptic segmentation · 33 citations (OpenAlex)

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
use segment loss normalization with λ=0.5 rather than pixel-averaged loss (ablation)PCV · COCO valPQ: 32.9 -> 37.5Improved
use segment loss normalization with λ=0.5 rather than pixel-averaged loss (ablation)PCV · COCO valPQth: 33.0 -> 40.0Improved
increase loss normalization strength from λ=0.5 to full area normalization, λ=1.0 (ablation)PCV · COCO valPQst: 33.7 -> 28.6Hurt
replace the default 233-cell voting grid with the simple grid (ablation)PCV · COCO valPQ: 37.5 -> 33.3Hurt
replace the default 233-cell voting grid with the simple grid (ablation)PCV · COCO val oraclePQ: 90.1 -> 79.2Hurt
replace the default voting grid with evenly spaced uniform bins (ablation)PCV · COCO val oraclePQ: 90.1 -> 67.1Hurt
replace the default voting grid with evenly spaced uniform bins (ablation)PCV · Cityscapes val oraclePQ: 88.6 -> 66.1Hurt
use PCV instead of the strongest listed baseline, UPSNetpanoptic segmentation · COCO valPQ: 42.5 -> 37.5Hurt
use PCV instead of the strongest listed baseline, UPSNetpanoptic segmentation · Cityscapes valPQ: 59.3 -> 54.2Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 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