List your company

Object Detection on VisDrone (test)

65.8AP50DroneFINE-L
-0.2416.90534.0551.195Mar 25, 2023Oct 10, 2023Apr 26, 2024Nov 11, 2024May 29, 2025Dec 14, 2025Jul 1, 2026

Evaluation results

MethodLinks
DroneFINE-LBackbone=Swin-L2026.0765.8—42.3—————————
RT-OVADBackbone=ResNet-502026.0764.6———————————
+Both (ZoomDet + DG.)Zooming Type=Patch-based zooming (Pat.Z.), F.P. (GFlops)=329.42026.0262.6—38.1———31.448.653.5———
UFPMP-DetBackbone=ResNet-502026.0762.4—36.6—————————
ESODBackbone=YOLOv52026.0762.3—37.9—————————
RemDet-XBackbone=YOLOv8X2026.0761.9—40—————————
DroneFINE-BBackbone=Swin-B2026.0761.9—38.8—————————
DG.Zooming Type=Patch-based zooming (Pat.Z.), F.P. (GFlops)=305.92026.0261.7—37.4———30.247.352———
DroneFINE-TBackbone=Swin-T2026.0761.2—38.4—————————
Dome-DETRBackbone=HGNetv2L2026.0761.1—39—————————
+Both (ZoomDet + ESOD)Zooming Type=Patch-based zooming (Pat.Z.), F.P. (GFlops)=141.62026.0260.3—36.8———29.346.944.9———
ZoomDetZooming Type=Patch-based zooming (Pat.Z.), F.P. (GFlops)=210.22026.0260.2—35.1———28.144.744.3———
ZoomDetZooming Type=Patch-based zooming (Pat.Z.), F.P. (GFlops)=158.72026.0260.1—36.3———28.446.952.8———
ESODZooming Type=Patch-based zooming (Pat.Z.), F.P. (GFlops)=135.42026.0259.7—36———28.345.945———
BaseZooming Type=Patch-based zooming (Pat.Z.), F.P. (GFlops)=153.02026.0258.8—34.8———26.446.353.2———
BaseZooming Type=Patch-based zooming (Pat.Z.), F.P. (GFlops)=202.12026.0257.7—33.9———25.542.743.7———
LAE-DINOBackbone=Swin-T2026.0756.4———————————
YOLO-WorldBackbone=YOLOv8L2026.0755.3———————————
YOLC(k=1)(Ours)Backbone=HRNet + MoonNet(1+tanh)2025.0955—32.933.6————————
ClusDetBackbone=ResNeXt1012025.0953.2—28.426.4————————
YOLC(k=1)(Ours)Backbone=HRNet + MoonNet(sigmoid)2025.0953—3131.1————————
YOLC(k=1)Backbone=HRNet2025.0951.6—30.330.7————————
CEASCBase Detector=GFL V1 [21], Backbone=ResNet182023.0350.7—28.728.4150.1821.55——————
CEASCBackbone=ResNet-502026.0750.7—28.7—————————
ClusDetBackbone=ResNet-502026.0750.6—26.7—————————
ClusDetBackbone=ResNet1012025.0950.4—26.725.2————————
MobileNet V2Base Detector=GFL V1 [21], Backbone=MobileNet V22023.0350.2—28.528.1491.4713.63——————
BaselineBase Detector=GFL V1 [21], Backbone=ResNet182023.0350—28.427.8524.9513.46——————
+Both (ZoomDet + RAF.)Zooming Type=Implicit zooming (Imp.Z.), F.P. (GFlops)=77.82026.0249.3—30.9———2145.357.9———
DMNetBackbone=ResNext1012025.0949.3—29.430.6————————
ZoomDetZooming Type=Uniform zooming (Uni.Z.), F.P. (GFlops)=21.22026.0248.5—27.5———16.942.560.7———
RAF.Zooming Type=Implicit zooming (Imp.Z.), F.P. (GFlops)=72.02026.0248.5—30———19.544.158.6———
DMNetBackbone=ResNet1012025.0948.1—28.529.4————————
QueryDetBackbone=ResNet-502026.0748.1—28.3—————————
Fe.-S.Zooming Type=Uniform zooming (Uni.Z.), F.P. (GFlops)=73.72026.0247.8—27———16.641.859.8———
+Both (ZoomDet + Rem.)Zooming Type=Implicit zooming (Imp.Z.), F.P. (GFlops)=39.62026.0247.5—29.2———19.443.755.8———
ZoomDetZooming Type=Implicit zooming (Imp.Z.), F.P. (GFlops)=74.12026.0247—28.9———18.64357.1———
ShuffleNet V2Base Detector=GFL V1 [21], Backbone=ShuffleNet V22023.0346.6—26.225.7488.9413.92——————
Rem.Zooming Type=Implicit zooming (Imp.Z.), F.P. (GFlops)=34.42026.0246.1—28.2———18.241.751———
BaseZooming Type=Uniform zooming (Uni.Z.), F.P. (GFlops)=16.42026.0244.9—25.5———14.439.957.2———
ZoomDetZooming Type=Uniform zooming (Uni.Z.), F.P. (GFlops)=128.92026.0244.6—26.1———15.540.257———
ZoomDetBase Detector=YOLOv8, FLOPs=48.22026.0244.4—25.9———15.739.157.81.241.181.05
SR4I.Zooming Type=Uniform zooming (Uni.Z.), F.P. (GFlops)=126.62026.0244.2—25.8———15.539.757.1———
ZoomDetZooming Type=Implicit zooming (Imp.Z.), F.P. (GFlops)=45.32026.0243.8—26.8———1739.950.2———
BaseZooming Type=Uniform zooming (Uni.Z.), F.P. (GFlops)=123.12026.0243.7—25———13.93956.7———
BaseZooming Type=Implicit zooming (Imp.Z.), F.P. (GFlops)=68.22026.0243.5—26.6———15.939.248.6———
SaliencyBase Detector=YOLOv8, Strategy=saliency parametrization, FLOPs=48.12026.0243.4—25.1———14.238.556.91.21.171.11
FOVEABase Detector=YOLOv8, FLOPs=48.62026.0243.3—25.4———14.838.857.91.181.131.07
LZUBase Detector=YOLOv8, FLOPs=49.02026.0242.8—24.9———14.138.558.5———
UniformBase Detector=YOLOv8, Strategy=uniform downsampling baseline, FLOPs=43.72026.0242.6—24.6———13.738.358.2111
BaseZooming Type=Implicit zooming (Imp.Z.), F.P. (GFlops)=39.52026.0240.5—24.4———14.536.746———
BaselineBase Detector=RetinaNet [22], Backbone=ResNet502023.0336.9—20.219.5586.7710.27——————
QueryDetBase Detector=RetinaNet [22], Backbone=ResNet502023.0335.7—19.619—10.65——————
QueryDet-CSQBase Detector=RetinaNet [22], Backbone=ResNet502023.0335—19.318.9—11.71——————
CEASCBase Detector=RetinaNet [22], Backbone=ResNet502023.0335—20.827.7201.9614.27——————
RS-MPODPrompt=visual-322026.025.5———————————
GroundingDINOPrompt=text2026.024.7———————————
RS-MPODPrompt=multimodal2026.024.6———————————
RS-MPODPrompt=text2026.023.8———————————
LAE-DINOPrompt=text2026.022.3———————————