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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add FPM to the CAT-Seg baseline (ablation) | CAT-Seg baseline · Pascal-Part | mIoU (%): 58.69 -> 59.10 | Improved |
| add COGM on top of FPM (ablation) | KPS · Pascal-Part | mIoU (%): 59.10 -> 60.24 | Improved |
| add SKGM on top of FPM and COGM (ablation) | KPS · Pascal-Part | mIoU (%): 60.24 -> 62.42 | Improved |
| add SKGM on top of FPM and COGM (ablation) | KPS · Pascal-Part | mACC (%): 70.11 -> 72.13 | Improved |
| use LLM-derived true part structure graph instead of fully connected graph (ablation) | KPS · Pascal-Part | mIoU (%): 60.47 -> 62.42 | Improved |
| use LLM-derived true part structure graph instead of within-object connections (ablation) | KPS · Pascal-Part | mIoU (%): 61.21 -> 62.42 | Improved |
| use 2 GCN layers instead of 1 (ablation) | KPS · Pascal-Part | mIoU (%): 60.75 -> 62.42 | Improved |
| use 3 GCN layers instead of 2 (ablation) | KPS · Pascal-Part | mIoU (%): 62.42 -> 61.82 | Hurt |
| use 4 GCN layers instead of 2 (ablation) | KPS · Pascal-Part | mIoU (%): 62.42 -> 61.78 | Hurt |
| replace CAT-Seg with KPS | CAT-Seg · PartImageNet | mIoU (%): 67.73 -> 72.69 | Improved |
| replace CAT-Seg with KPS | CAT-Seg · Pascal-Part | mIoU (%): 58.69 -> 62.42 | Improved |
| replace CAT-Seg with KPS | CAT-Seg · Pascal-Part-116 | hIoU (%): 26.72 -> 33.92 | Improved |
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.
- Compositor — Compositor: Bottom-Up Clustering and Compositing for Robust Part and Object Segmentation (CVPR 2023) · better on 4 of 4 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
- Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation (CVPR 2025 · similarity 0.89)
- PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding (NeurIPS 2025 · similarity 0.89)
- PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding (NeurIPS 2025 · similarity 0.88)
- Understanding Multi-Granularity for Open-Vocabulary Part Segmentation (NeurIPS 2024 · similarity 0.88)
- Imagine: Image-Guided 3D Part Assembly with Structure Knowledge Graph (AAAI 2025 · similarity 0.88)
- SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation (NeurIPS 2025 · similarity 0.87)
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.
