Research map / Detection and segmentation / CNN features
EfficientPS: Efficient Panoptic Segmentation
Rohit Mohan, Abhinav Valada
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 |
|---|---|---|---|
| pre-train on Mapillary Vistas | EfficientPS · Cityscapes val (single-scale) | PQ (%): 63.9 -> 66.1 | Improved |
| pre-train on Mapillary Vistas | EfficientPS · Cityscapes val (multi-scale) | PQ (%): 65.1 -> 67.5 | Improved |
| multi-scale evaluation | EfficientPS · Cityscapes val | PQ (%): 63.9 -> 65.1 | Improved |
| multi-scale evaluation | EfficientPS · Mapillary Vistas val | PQ (%): 38.3 -> 40.5 | Improved |
| multi-scale evaluation | EfficientPS · KITTI val | PQ (%): 42.9 -> 43.7 | Improved |
| pre-train on Mapillary Vistas | EfficientPS · Cityscapes test | PQ (%): 64.1 -> 67.1 | Improved |
| use EfficientPS instead of Panoptic-Deeplab | panoptic segmentation model · Cityscapes val (single-scale, no pre-training) | PQ (%): 63.0 -> 63.9 | Improved |
| use EfficientPS instead of Panoptic-Deeplab | panoptic segmentation model · Cityscapes test (no pre-training) | PQ (%): 62.3 -> 64.1 | Improved |
| use EfficientPS instead of Seamless | panoptic segmentation model · Cityscapes efficiency | parameters and time: 51.43 -> 40.89 M params; 168 -> 166 ms | Improved |
| use EfficientPS instead of Panoptic-Deeplab | panoptic segmentation model · KITTI/Vistas efficiency | FLOPs: 547.49 -> 433.94 GFLOPs | Improved |
Later papers that compared with this method
1 later accepted paper reports EfficientPS as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Improving Panoptic Segmentation at All Scales (CVPR 2021 · better on 5 of 5 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- Panoptic-DeepLab — Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation (CVPR 2020) · better on 12 of 12 shared results
- UPSNet — UPSNet: A Unified Panoptic Segmentation Network (CVPR 2019) · better on 3 of 3 shared results
- AdaptIS — AdaptIS: Adaptive Instance Selection Network (ICCV 2019) · better on 2 of 2 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, Instance and Semantic Relations: A Relational Context Encoder To Enhance Panoptic Segmentation (CVPR 2022 · similarity 0.89)
- Seamless Scene Segmentation (CVPR 2019 · similarity 0.89)
- Real-Time Panoptic Segmentation From Dense Detections (CVPR 2020 · similarity 0.88)
- Unifying Training and Inference for Panoptic Segmentation (CVPR 2020 · similarity 0.88)
- SGFormer: Semantic-Geometry Fusion Transformer for Multi-modal 3D Panoptic Segmentation (AAAI 2025 · similarity 0.87)
- Scene-Centric Unsupervised Panoptic Segmentation (CVPR 2025 · similarity 0.86)
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.
