AI Paper Atlas

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

ICML 2026 · Detection and segmentation › CNN features · approach: Efficient DETR query design

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 changedWhereMeasuredEffect
use heterogeneous routed MoE (shared + task-specific + dynamic experts) instead of standard MoE (ablation)DroneDINO · 5 Drone-UOD tasksAP change: -1.56 when replaced by standard MoEImproved
add HR-MoE module (ablation)DroneDINO · 5 Drone-UOD tasksAP change: -2.10 when removedImproved
add task-recognition auxiliary head (ablation)DroneDINO · 5 Drone-UOD tasksAP change: -0.36 average; T1 +0.6, T5 -1.7 when removedMixed
unified multi-task training instead of separate training (ablation)DroneDINO · T4/T5 RGBTDronePersonAP change: -18.1 (T4), -15.8 (T5) when removedImproved
increase total experts from 4 to 8 (ablation)HR-MoE dynamic group · DroneVehicleAP: 63.3 -> 63.6Improved
increase total experts from 8 to 16 (ablation)HR-MoE dynamic group · DroneVehicleAP: 63.6 -> 63.3Hurt
activate top-4 of 8 experts instead of 2 (ablation)HR-MoE · DroneVehicleAP: 63.6 -> 63.9Improved
use fully dense execution (top-8) instead of sparse top-4 (ablation)HR-MoE · DroneVehicleAP: 63.9 -> 63.0Hurt
unified DroneDINO versus task-specific RTMDet on RGB-IRDroneDINO · DroneVehicle RGB-IRAP: 53.2 -> 64.5Improved
unified DroneDINO versus UAV-DETRDroneDINO · VisDroneAP: 31.5 vs 30.2Hurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy