Research map / Detection and segmentation / Open-set and few-shot detection
Playing for Benchmarks
Stephan R. Richter, Zeeshan Hayder, Vladlen Koltun
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 |
|---|---|---|---|
| train on all weather/time conditions instead of day and sunset only (ablation) | MNC · VIPER instance segmentation (all) | AP: 6.2 -> 7.7 | Improved |
| train on all weather/time conditions instead of day and sunset only (ablation) | BAIS · VIPER instance segmentation (all) | AP: 9.6 -> 12.6 | Improved |
| train on all conditions instead of day and sunset only (ablation) | BAIS · VIPER instance segmentation (night) | AP: 3.1 -> 11.6 | Improved |
| train on all conditions instead of day and sunset only (ablation) | MNC · VIPER instance segmentation (night) | AP: 2.3 -> 5.4 | Improved |
| train on all conditions instead of day and sunset only (ablation) | BAIS · VIPER instance segmentation (sunset) | AP: 12.4 -> 11.5 | Hurt |
| use PSPNet instead of FCN-ResNet | semantic segmentation · VIPER semantic segmentation (all) | mean IoU: 55.1 -> 68.9 | Improved |
| move evaluation from Cityscapes to VIPER | PSPNet · VIPER vs Cityscapes | mean IoU: above 80% -> 69% | Hurt |
| move evaluation from Cityscapes to VIPER | BAIS · VIPER vs Cityscapes | AP: 17.4 -> 12.6 | Hurt |
| change condition from day to night | FlowFields · VIPER optical flow | weighted AUC: 78.4 -> 60.2 | Hurt |
| change condition from day to rain | EpicFlow · VIPER optical flow | weighted AUC: 76.8 -> 52.4 | Hurt |
| use DSO instead of ORB-SLAM2 | visual odometry · VIPER visual odometry (all) | rotation error (deg/m): 0.341 -> 0.245 | Improved |
| change condition from day to sunset | ORB-SLAM2 · VIPER visual odometry | rotation error (deg/m): 0.253 -> 0.420 | Hurt |
Closest papers by meaning
- OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection (NeurIPS 2025 · similarity 0.89)
- Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark (CVPR 2023 · similarity 0.88)
- InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity (CVPR 2026 · similarity 0.88)
- RCP-Bench: Benchmarking Robustness for Collaborative Perception Under Diverse Corruptions (CVPR 2025 · similarity 0.86)
- DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videos (CVPR 2024 · similarity 0.86)
- Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications (CVPR 2024 · 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.
