AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Personalized Image Semantic Segmentation

Yu Zhang, Chang-Bin Zhang, Peng-Tao Jiang, Ming-Ming Cheng, Feng Mao

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 6 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 group region context module (ablation)ADVENT baseline (VGG-16) · PSSFIoU: 44.22 -> 47.16Improved
use global group context instead of no context (ablation)ADVENT baseline (VGG-16) · PSSFIoU: 44.22 -> 44.56No clear effect
add pseudo label refinement step (ablation)OURS-S1 (ResNet-50) · PSSFIoU: 58.79 -> 59.72Improved
add pseudo label refinement step (ablation)OURS-S1 (ResNet-50) · PSSMIoU: 37.46 -> 39.16Improved
add group context module to ADVENT (ablation)ADVENT (ResNet-50) · PSSMIoU: 37.31 -> 37.46No clear effect
add group context module to ADVENT (ablation)ADVENT (ResNet-50) · PSSFIoU: 56.59 -> 58.79Improved
train on personal data instead of mixing all users' images (ablation)OURS (VGG-16) · PSSFIoU: 45.56 -> 47.16Improved
use 80 groups instead of 1 group (ablation)OURS (VGG-16) · PSSFIoU: 46.64 -> 47.16Improved
use 80 groups instead of 200 groups (ablation)OURS (VGG-16) · PSSFIoU: 46.66 -> 47.16Improved
add group context module to ADVENT (ablation)ADVENT (ResNet-101) · GTA5 to CityscapesmIoU: 43.8 -> 45.4Improved
add group context module (OURS-S1 vs baseline without context) (ablation)Baseline (ResNet-50), user ID6 · PSS ID6MIoU: 40.52 -> 33.64Hurt
add group context module (OURS-S1 vs baseline without context) (ablation)Baseline (ResNet-50), user ID6 · PSS ID6FIoU: 55.04 -> 60.38Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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