Research map / Detection and segmentation / CNN features
Delving Into Robust Object Detection From Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach
Zhenyu Wu, Karthik Suresh, Priya Narayanan, Hongyu Xu, Heesung Kwon, Zhangyang Wang
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 altitude nuisance disentanglement (gamma1=0.03) (ablation) | Faster-RCNN · UAVDT (vehicle) | AP: 45.64 -> 45.92 | Improved |
| add view nuisance disentanglement (gamma2=0.01) (ablation) | Faster-RCNN · UAVDT (vehicle) | AP: 45.64 -> 46.16 | Improved |
| add weather nuisance disentanglement (gamma3=0.01) (ablation) | Faster-RCNN · UAVDT (vehicle) | AP: 45.64 -> 46.62 | Improved |
| raise altitude gamma1 from 0.03 to 0.05 (ablation) | NDFT altitude only · UAVDT (vehicle) | AP: 45.92 -> 44.36 | Hurt |
| raise weather gamma3 from 0.01 to 0.1 (ablation) | NDFT weather only · UAVDT (vehicle) | AP: 46.62 -> 43.60 | Hurt |
| add weather disentanglement on night images (ablation) | Faster-RCNN · UAVDT (night) | AP: 52.14 -> 59.66 | Improved |
| combine altitude and view disentanglement (ablation) | NDFT · UAVDT (vehicle) | AP: 46.16 -> 46.88 | Improved |
| add weather to altitude and view disentanglement (ablation) | NDFT A+V · UAVDT (vehicle) | AP: 46.88 -> 47.91 | Improved |
| replace Faster-RCNN with FPN backbone in NDFT | NDFT A+V+W · UAVDT (vehicle) | AP: 49.05 -> 52.03 | Improved |
| use adversarial nuisance loss instead of auxiliary multi-task loss (ablation) | NDFT · UAVDT (vehicle) | AP: 45.69 -> 46.81 | Improved |
| add NDFT to detections used by SORT tracker | SORT tracking · UAVDT MOT | IDF: 43.7 -> 52.9 | Improved |
| add NDFT to detections used by SORT tracker | SORT tracking · UAVDT MOT | MOTA: 39.0 -> 38.4 | Hurt |
Closest papers by meaning
- RemDet: Rethinking Efficient Model Design for UAV Object Detection (AAAI 2025 · similarity 0.89)
- Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (TPAMI 2021 · similarity 0.89)
- The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking (ECCV 2018 · similarity 0.88)
- FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection (AAAI 2024 · similarity 0.86)
- Detection-Friendly Nonuniformity Correction: A Union Framework for Infrared UAV Target Detection (CVPR 2025 · similarity 0.86)
- UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles (NeurIPS 2024 · 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.
