Research map / Detection and segmentation / CNN features
Panoptic, Instance and Semantic Relations: A Relational Context Encoder To Enhance Panoptic Segmentation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 PISR to Panoptic-DeepLab | Panoptic-DeepLab with ResNet-50 · Cityscapes val | PQ: 59.9 -> 62.2 | Helped |
| Add PISR to Panoptic-DeepLab | Panoptic-DeepLab with ResNet-50 · COCO val | PQ: 35.5 -> 38.8 | Helped |
| Add PISR to MaskFormer | MaskFormer with ResNet-101 · ADE20K val | PQ: 35.7 -> 37.0 | Helped |
| Add panoptic-encoding reweighting (ablation) | PISR with Panoptic-DeepLab, ResNet-50 · Cityscapes val | PQ: 61.8 -> 62.2 | Helped |
| Replace PISR with concatenation of semantic, instance, and global features (ablation) | Panoptic-DeepLab, ResNet-50 · Cityscapes val | PQ: 62.2 -> 60.6 | Hurt |
| Replace PISR with elementwise-product feature fusion (ablation) | Panoptic-DeepLab, ResNet-50 · Cityscapes val | PQ: 62.2 -> 60.4 | Hurt |
| Use OCR instead of PISR for relational feature processing (ablation) | Panoptic-DeepLab, ResNet-50 · Cityscapes val | PQ: 62.2 -> 60.7 | Hurt |
| Increase the number of selected instances K (ablation) | PISR with Panoptic-DeepLab · Cityscapes and COCO val | PQ | Mixed |
| Remove encoding reweighting while increasing K (ablation) | PISR with Panoptic-DeepLab · Cityscapes and COCO val | PQ | Hurt |
Closest papers by meaning
- Unifying Training and Inference for Panoptic Segmentation (CVPR 2020 · similarity 0.92)
- Video Panoptic Segmentation (CVPR 2020 · similarity 0.90)
- Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation (NeurIPS 2020 · similarity 0.90)
- LPSNet: A Lightweight Solution for Fast Panoptic Segmentation (CVPR 2021 · similarity 0.90)
- Panoptic Segmentation (CVPR 2019 · similarity 0.90)
- Scene-Centric Unsupervised Panoptic Segmentation (CVPR 2025 · similarity 0.89)
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.