Research map / Detection and segmentation / Open-set and few-shot detection
SkyScapes Fine-Grained Semantic Understanding of Aerial Scenes
Seyed Majid Azimi, Corentin Henry, Lars Sommer, Arne Schumann, Eleonora Vig
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 |
|---|---|---|---|
| use SkyScapesNet (multi-task, FDB, FRSR, CRASPP, LKBR) instead of the best benchmark segmentation model | SkyScapesNet · SkyScapes-Dense (20 classes) | mIoU: 1.93% mIoU improvement | Improved |
| use SkyScapesNet instead of the best baseline | SkyScapesNet · SkyScapes-Lane (13 classes) | mIoU: 51.93% mIoU, outperforming the state of the art by 3.06% | Improved |
| add both binary and multi-class edge detection branches as auxiliary tasks (ablation) | SkyScapesNet · SkyScapes-Dense (20 classes) | mIoU | Improved |
Closest papers by meaning
- Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery (CVPR 2024 · similarity 0.88)
- Predicting Ground-Level Scene Layout From Aerial Imagery (CVPR 2017 · similarity 0.88)
- The Cityscapes Dataset for Semantic Urban Scene Understanding (CVPR 2016 · similarity 0.88)
- SkyScenes: A Synthetic Dataset for Aerial Scene Understanding (ECCV 2024 · similarity 0.87)
- Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges (CVPR 2021 · similarity 0.87)
- SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes (CVPR 2025 · similarity 0.85)
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.
