Research map / Detection and segmentation / CNN features
DroneDINO: Towards Heterogeneous Routed Mixture of Experts for Drone-based Unified Object Detection
Dongdong Li, Rui Chen, Yan Fan, Yan Liu, Yangliu Kuai, Pengfei Zhu
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 heterogeneous routed MoE (shared + task-specific + dynamic experts) instead of standard MoE (ablation) | DroneDINO · 5 Drone-UOD tasks | AP change: -1.56 when replaced by standard MoE | Improved |
| add HR-MoE module (ablation) | DroneDINO · 5 Drone-UOD tasks | AP change: -2.10 when removed | Improved |
| add task-recognition auxiliary head (ablation) | DroneDINO · 5 Drone-UOD tasks | AP change: -0.36 average; T1 +0.6, T5 -1.7 when removed | Mixed |
| unified multi-task training instead of separate training (ablation) | DroneDINO · T4/T5 RGBTDronePerson | AP change: -18.1 (T4), -15.8 (T5) when removed | Improved |
| increase total experts from 4 to 8 (ablation) | HR-MoE dynamic group · DroneVehicle | AP: 63.3 -> 63.6 | Improved |
| increase total experts from 8 to 16 (ablation) | HR-MoE dynamic group · DroneVehicle | AP: 63.6 -> 63.3 | Hurt |
| activate top-4 of 8 experts instead of 2 (ablation) | HR-MoE · DroneVehicle | AP: 63.6 -> 63.9 | Improved |
| use fully dense execution (top-8) instead of sparse top-4 (ablation) | HR-MoE · DroneVehicle | AP: 63.9 -> 63.0 | Hurt |
| unified DroneDINO versus task-specific RTMDet on RGB-IR | DroneDINO · DroneVehicle RGB-IR | AP: 53.2 -> 64.5 | Improved |
| unified DroneDINO versus UAV-DETR | DroneDINO · VisDrone | AP: 31.5 vs 30.2 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 2 of 2 shared results
- SM3Det — SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection (AAAI 2026) · better on 1 of 1 shared result
- PlainDet — Plain-Det: A Plain Multi-Dataset Object Detector (ECCV 2024) · better on 1 of 1 shared result
- QueryDet — QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection (CVPR 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PointSR: Self-Regularized Point Supervision for Drone-View Object Detection (CVPR 2025 · similarity 0.85)
- RemDet: Rethinking Efficient Model Design for UAV Object Detection (AAAI 2025 · similarity 0.84)
- Multiview Aerial Visual RECognition (MAVREC): Can Multi-view Improve Aerial Visual Perception? (CVPR 2024 · similarity 0.84)
- A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding (NeurIPS 2025 · similarity 0.84)
- FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection (AAAI 2025 · similarity 0.83)
- FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection (AAAI 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.
