Research map / Detection and segmentation / CNN features
Panoptic-PartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation
Xiangtai Li, Shilin Xu, Yibo Yang, Haobo Yuan, Guangliang Cheng, Yunhai Tong, Zhouchen Lin, Ming–Hsuan Yang, Dacheng Tao
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 decoupled decoder (ablation) | Panoptic-PartFormer · Cityscapes PPS val (ResNet50) | PartPQ: 55.9 -> 57.4 | Improved |
| add dynamic convolution (ablation) | Panoptic-PartFormer · Cityscapes PPS val (ResNet50) | PartPQ: 52.2 -> 57.4 | Improved |
| add self attention among queries (ablation) | Panoptic-PartFormer · Cityscapes PPS val (ResNet50) | PartPQ: 53.4 -> 57.4 | Improved |
| joint reasoning over stuff, thing and part queries instead of separate (ablation) | Panoptic-PartFormer · Cityscapes PPS val (ResNet50) | PartPQ: 56.8 -> 57.4 | Improved |
| joint query part prediction instead of dense prediction head (ablation) | Panoptic-PartFormer · Cityscapes PPS val (ResNet50) | PartPQ: 55.9 -> 57.4 | Improved |
| add aligned part decoder (ablation) | Panoptic-PartFormer · Cityscapes PPS val (ResNet50) | PartPQ: 56.3 -> 57.4 | Improved |
| add positional encoding (ablation) | Panoptic-PartFormer · Cityscapes PPS val (ResNet50) | PartPQ: 55.1 -> 57.4 | Improved |
| add boundary loss supervision (ablation) | Panoptic-PartFormer · Cityscapes PPS val (ResNet50) | PartPQ: 57.4 -> 57.2 | No clear effect |
| add decoupled decoder (ablation) | Panoptic-PartFormer++ · Cityscapes PPS val (ResNet50) | PartPQ: 58.0 -> 59.2 | Improved |
| add part masked cross attention (ablation) | Panoptic-PartFormer++ · Cityscapes PPS val (ResNet50) | PartPQ: 58.5 -> 59.2 | Improved |
| global-first reasoning instead of part-first (ablation) | Panoptic-PartFormer++ · Cityscapes PPS val (ResNet50) | PartPQ: 58.3 -> 59.2 | Improved |
| use part query merge instead of dense prediction head merge (ablation) | Panoptic-PartFormer++ · Cityscapes PPS val (ResNet50) | PartPQ: 57.4 -> 59.2 | 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.
- Panoptic-PartFormer — Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation (ECCV 2022) · better on 6 of 6 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
- Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation (ECCV 2022 · similarity 0.98)
- Part-Aware Panoptic Segmentation (CVPR 2021 · similarity 0.94)
- Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations (CVPR 2024 · similarity 0.91)
- Unifying Training and Inference for Panoptic Segmentation (CVPR 2020 · similarity 0.90)
- Scene-Centric Unsupervised Panoptic Segmentation (CVPR 2025 · similarity 0.88)
- PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding (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.
