Research map / Detection and segmentation / Open-set and few-shot detection
AVOIDDS: Aircraft Vision-based Intruder Detection Dataset and Simulator
Elysia Quinn Smyers, Sydney Michelle Katz, Anthony Corso, Mykel Kochenderfer
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 conditions rather than nominal-only subset (ablation) | YOLOv8s detector · AVOIDDS test set | mAP: 0.764 -> 0.866 | Improved |
| train on all conditions rather than nominal-only subset (ablation) | YOLOv8s detector · AVOIDDS test set | precision: 0.884 -> 0.997 | Improved |
| train on all conditions rather than nominal-only subset (ablation) | YOLOv8s detector · AVOIDDS test set | recall: 0.928 -> 0.907 | Mixed |
| train on all regions rather than only Palo Alto (ablation) | YOLOv8s detector · Boston test images | mAP: 0.722 -> 0.885 | Improved |
| train on all regions rather than only Palo Alto (ablation) | YOLOv8s detector · Palo Alto test images | mAP: 0.865 -> 0.900 | No clear effect |
| include late afternoon images in training (ablation) | YOLOv8s detector · Late afternoon test images | mAP: 0.657 -> 0.846 | Improved |
| train on all conditions rather than nominal-only subset (ablation) | YOLOv8s detector · Downstream encounters | NMAC frequency: 0.165 -> 0.143 | Improved |
| train on all conditions rather than nominal-only subset (ablation) | YOLOv8s detector · Downstream encounters | advisory frequency: 0.191 -> 0.187 | No clear effect |
| increase intruder range from 0-150 m to >500 m | YOLOv8s detector · AVOIDDS test set | mAP: 0.979 -> 0.714 | Hurt |
| Boeing 737-800 intruder instead of Cessna Skyhawk | YOLOv8s detector · AVOIDDS test set | mAP: 0.750 -> 0.983 | Improved |
| late afternoon time of day vs other times | YOLOv8s detector · Downstream encounters (alt model) | NMAC frequency: 0.148 -> 0.181 | Hurt |
| train on all regions rather than only Palo Alto (ablation) | YOLOv8s detector · Reno downstream encounters | NMAC frequency: 0.180 -> 0.141 | Improved |
Closest papers by meaning
- Delving Into Robust Object Detection From Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach (ICCV 2019 · similarity 0.85)
- LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models (ICML 2025 · similarity 0.84)
- A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding (NeurIPS 2025 · similarity 0.83)
- YOLOv10: Real-Time End-to-End Object Detection (NeurIPS 2024 · similarity 0.83)
- OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection (NeurIPS 2025 · similarity 0.83)
- UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles (NeurIPS 2024 · similarity 0.83)
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.
