AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence

Sangryul Jeon, Seungryong Kim, Dongbo Min, Kwanghoon Sohn

ECCV 2018 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 57 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 level 2 on top of level 1 (ablation)PARN (VGG-16) · Taniai benchmark (average)matching accuracy: 0.697 -> 0.739Improved
add level 3 on top of level 2 (ablation)PARN (VGG-16) · Taniai benchmark (average)matching accuracy: 0.739 -> 0.752Improved
add pixel-level module on top of level 3 (ablation)PARN (VGG-16) · Taniai benchmark (average)matching accuracy: 0.752 -> 0.760Improved
replace VGG-16 with ResNet-101 backbonePARN · Taniai benchmark (average)matching accuracy: 0.760 -> 0.788Improved
train level-1 module with semantic consistency supervision instead of synthetic deformationsPARN-Lv1 · Taniai benchmark (average)matching accuracy: 0.644 -> 0.697Improved
add bilinear upsampling after each grid-level regression (ablation)PARN · Taniai qualitativeartifact smoothnessImproved
use PARN instead of SCNet on PF-PASCAL at alpha=0.1SCNet · PF-PASCALPCK: 0.482 -> 0.491Improved
use PARN instead of SCNet on PF-PASCAL at alpha=0.05SCNet · PF-PASCALPCK: 0.260 -> 0.268Improved
use PARN instead of DCTM on Caltech-101DCTM · Caltech-101LT-ACC: 0.84 -> 0.87Improved
use PARN instead of DCTM on Caltech-101DCTM · Caltech-101LOC-ERR: 0.18 -> 0.21Hurt
use PARN instead of DCTM on Caltech-101DCTM · Caltech-101IoU: 0.53 -> 0.65Improved
use PARN instead of OHG on Taniai PASCAL subsetOHG · Taniai benchmark (PASCAL)matching accuracy: 0.729 -> 0.688Hurt

Later papers that compared with this method

1 later accepted paper reports PARN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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