Research map / Detection and segmentation / Open-set and few-shot detection
Vehicle Perception From Satellite
Bin Zhao, Pengfei Han, Xuelong Li
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 synthetic GTA-V data to real training data (ablation) | RAZNet · TMS TOD | F-score: 47.53 -> 56.78 | Improved |
| add synthetic data (ablation) | YOLO v4 · TMS TOD | F-score: 22.00 -> 31.00 | Improved |
| add synthetic data (ablation) | YOLO v6 · TMS TOD | F-score: 36.43 -> 37.6 | Improved |
| add synthetic data (ablation) | YOLO v5 · TMS TOD | F-score: 32.2 -> 33.5 | Improved |
| add synthetic data (ablation) | YOLO v8 · TMS TOD | F-score: 39.81 -> 35.9 | Hurt |
| add synthetic data (ablation) | Dino · TMS TOD | F-score: 9.7 -> 12.3 | Improved |
| add synthetic data (ablation) | CSRNet · TMS vehicle counting | MAE: 6.75 -> 6.02 | Improved |
| add synthetic data (ablation) | SCAR · TMS vehicle counting | MAE: 6.70 -> 5.79 | Improved |
| add synthetic data (ablation) | MCNN · TMS vehicle counting | MAE: 7.15 -> 6.92 | Improved |
| add synthetic data (ablation) | RAZNet · TMS vehicle counting | MAE: 7.17 -> 6.74 | Improved |
| add synthetic data (ablation) | SFCN+ · TMS vehicle counting | MAE: 4.75 -> 12.34 | Hurt |
| add synthetic data (ablation) | Faster RCNN · TMS TOD | F-score: 3.00 -> 2.00 | Hurt |
Closest papers by meaning
- TrafficNight : An Aerial Multimodal Benchmark For Nighttime Vehicle Surveillance (ECCV 2024 · similarity 0.82)
- Traffic Scene Parsing through the TSP6K Dataset (CVPR 2024 · similarity 0.82)
- Satformer: Accurate and Robust Traffic Data Estimation for Satellite Networks (NeurIPS 2024 · similarity 0.81)
- On-Road Object Importance Estimation: A New Dataset and A Model with Multi-Fold Top-Down Guidance (NeurIPS 2024 · similarity 0.81)
- UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception (NeurIPS 2025 · similarity 0.80)
- eTraM: Event-based Traffic Monitoring Dataset (CVPR 2024 · similarity 0.80)
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.
