AI Paper Atlas

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

Open World Entity Segmentation

Lu Qi, Jason Kuen, Yi Wang, Jiuxiang Gu, Hengshuang Zhao, Philip H. S. Torr, Zhe Lin, Jiaya Jia

TPAMI 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 74 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 global kernel bank (L_R^seg) to class-agnostic CondInst (ablation)Entity segmentation framework · COCO val (ES)AP_e^m: 28.3 -> 29.3Improved
add overlap suppression (L_o^seg) to class-agnostic CondInst (ablation)Entity segmentation framework · COCO val (ES)AP_e^m: 28.3 -> 29.1Improved
add both global kernel bank and overlap suppression (ablation)Entity segmentation framework · COCO val (ES)AP_e^m: 28.3 -> 29.8Improved
use softmax instead of sigmoid in overlap suppression loss (ablation)Overlap suppression · COCO val (ES)AP_e^m: 28.6 -> 29.1Improved
add sigmoid loss on top of softmax in overlap suppression (ablation)Overlap suppression · COCO val (ES)AP_e^m: 29.1 -> 29.0No clear effect
add static kernels in last one or two mask head layers (ablation)Dynamic-kernel mask head · COCO val (ES)AP_e^m: 28.3 -> 28.9 -> 29.1Improved
train all seven kernel-bank paths (ablation)Global kernel bank · COCO val (ES)AP_e^m: 28.3 -> 29.3Improved
use all paths at inference instead of last path (ablation)Global kernel bank · COCO val (ES)AP_e^m: 29.8 -> 30.0No clear effect
add the two modules under 36-epoch schedule (ablation)Class-agnostic CondInst · COCO val (ES, 36 epochs)AP_e^m: 30.4 -> 31.8Improved
train class-agnostic instead of class-specificPanopticFCN · COCO val (ES, 12 epochs)AP_e^m: 24.5 -> 26.5Improved
train on COCO+ADE20K merged without resolving label conflictsEntity segmentation model · ADE20K val (12 epochs)AP_e^m: 24.1 -> 26.3Improved
represent stuff by nine points instead of single center point (ablation)Center-based stuff representation · COCO stuffAP_e^m: 39.4 -> 40.2Improved

Earlier methods this paper compares with

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