AI Paper Atlas

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

Knowledge-Guided Part Segmentation

Xuejian Gou, Fang Liu, Licheng Jiao, Shuo Li, Lingling Li, Hao Wang, Xu Liu, Puhua Chen, Wenping Ma

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary 3D and world perception · 3 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 FPM to the CAT-Seg baseline (ablation)CAT-Seg baseline · Pascal-PartmIoU (%): 58.69 -> 59.10Improved
add COGM on top of FPM (ablation)KPS · Pascal-PartmIoU (%): 59.10 -> 60.24Improved
add SKGM on top of FPM and COGM (ablation)KPS · Pascal-PartmIoU (%): 60.24 -> 62.42Improved
add SKGM on top of FPM and COGM (ablation)KPS · Pascal-PartmACC (%): 70.11 -> 72.13Improved
use LLM-derived true part structure graph instead of fully connected graph (ablation)KPS · Pascal-PartmIoU (%): 60.47 -> 62.42Improved
use LLM-derived true part structure graph instead of within-object connections (ablation)KPS · Pascal-PartmIoU (%): 61.21 -> 62.42Improved
use 2 GCN layers instead of 1 (ablation)KPS · Pascal-PartmIoU (%): 60.75 -> 62.42Improved
use 3 GCN layers instead of 2 (ablation)KPS · Pascal-PartmIoU (%): 62.42 -> 61.82Hurt
use 4 GCN layers instead of 2 (ablation)KPS · Pascal-PartmIoU (%): 62.42 -> 61.78Hurt
replace CAT-Seg with KPSCAT-Seg · PartImageNetmIoU (%): 67.73 -> 72.69Improved
replace CAT-Seg with KPSCAT-Seg · Pascal-PartmIoU (%): 58.69 -> 62.42Improved
replace CAT-Seg with KPSCAT-Seg · Pascal-Part-116hIoU (%): 26.72 -> 33.92Improved

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