Object Detection on DroneVehicle (test)
85mAP50InfraNet-RGB-IR
Evaluation Results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| InfraNet-RGB-IRMode=RGB+IR, Backbone=YOLOv82026.07 | 85 | 98.1 | 82.6 | 79.9 | 97.3 | 67.3 | — | — | 64.9 | — | — | |
| InfraNet-RGB-IRMode=RGB+IR, Backbone=YOLOv122026.07 | 84.8 | 98 | 82.6 | 78.3 | 97.3 | 67.6 | — | — | 64.7 | — | — | |
| InfraNet-IRMode=IR, Backbone=YOLOv122026.07 | 84.7 | 98.1 | 81.3 | 77.7 | 97.3 | 69.3 | — | — | 63.9 | — | — | |
| InfraNet-RGB-IRMode=RGB+IR, Backbone=YOLOv52026.07 | 84.1 | 98.1 | 82.1 | 76.2 | 97.2 | 67.1 | — | — | 63.8 | — | — | |
| InfraNet-IRMode=IR, Backbone=YOLOv82026.07 | 84 | 98 | 80 | 76.9 | 97 | 68.4 | — | — | 63.4 | — | — | |
| InfraNet-RGB-IRMode=RGB+IR, Backbone=ResNet502026.07 | 83.9 | 98 | 80.5 | 78 | 97.3 | 65.7 | — | — | 64.1 | — | — | |
| InfraNet-IRMode=IR, Backbone=YOLOv52026.07 | 83.6 | 98 | 79.6 | 75.5 | 96.9 | 68.2 | — | — | 63.1 | — | — | |
| InfraNet-IRMode=IR, Backbone=ResNet502026.07 | 83.5 | 97.8 | 79.3 | 75 | 97.1 | 68.3 | — | — | 63 | — | — | |
| PACGNetVisible=true, Infrared=true2025.12 | 82.2 | 98.5 | 83 | 68.7 | 96.3 | 64.3 | — | — | — | — | — | |
| PACGNetParams.(M)=5.2, GFLOPs=13.22025.12 | 82.2 | — | — | — | — | — | — | — | — | — | — | |
| RGFNetVisible=true, Infrared=true2025.12 | 81.4 | 98.4 | 81.1 | 68.7 | 95.8 | 63 | — | — | — | — | — | |
| SLGNet2026.01 | 80.7 | 96.1 | 80.9 | 69.4 | 91.8 | 65.3 | — | — | — | — | — | |
| MGMFVisible=true, Infrared=true2025.12 | 80.3 | 91.4 | 70.1 | 78.5 | 91.1 | 69.4 | — | — | — | — | — | |
| MGMFParams.(M)=122.02025.12 | 80.3 | — | — | — | — | — | — | — | — | — | — | |
| WaveMamba2026.01 | 79.8 | 95 | 80.4 | 68.5 | 90.6 | 64.5 | — | — | — | — | — | |
| WaveMambaMode=RGB+IR, Backbone=YOLOv82026.07 | 79.8 | 95 | 80.4 | 68.5 | 90.6 | 64.5 | — | — | 60.5 | — | — | |
| BabelRSOptimization Stage=Pretraining stage optimization2026.03 | 79.63 | — | — | — | — | — | — | — | 51.32 | — | — | |
| UniFusOD2026.01 | 79.5 | 96.4 | 81.3 | 63.5 | 90.8 | 65.6 | — | — | — | — | — | |
| WaveMambaMode=RGB+IR, Backbone=YOLOv52026.07 | 79.5 | 94.8 | 80.1 | 68.2 | 90.1 | 64.3 | — | — | 60.2 | — | — | |
| DMM2026.01 | 79.4 | 90.4 | 79.8 | 68.2 | 89.9 | 68.6 | — | — | — | — | — | |
| OAFAVisible=true, Infrared=true2025.12 | 79.4 | 90.3 | 76.8 | 73.3 | 90.3 | 66 | — | — | — | — | — | |
| WaveMambaMode=RGB+IR, Backbone=ResNet502026.07 | 79.3 | 94.6 | 79.6 | 68 | 90.2 | 64.1 | — | — | 59.9 | — | — | |
| M2FP2026.01 | 78.7 | 95.7 | 76.2 | 64.7 | 92.1 | 64.7 | — | — | — | — | — | |
| M2FPVisible=true, Infrared=true2025.12 | 78.7 | 95.7 | 76.2 | 64.7 | 92.1 | 64.7 | — | — | — | — | — | |
| DDCINetVisible=true, Infrared=true2025.12 | 78.4 | 91 | 78.9 | 66.1 | 90.7 | 65.5 | — | — | — | — | — | |
| SM3DetOptimization Stage=Fine-tuning stage optimization2026.03 | 77.99 | — | — | — | — | — | — | — | 48.87 | — | — | |
| Uncertainty lossOptimization Stage=Fine-tuning stage optimization2026.03 | 77.96 | — | — | — | — | — | — | — | 48.78 | — | — | |
| DAOptimization Stage=Fine-tuning stage optimization2026.03 | 77.43 | — | — | — | — | — | — | — | 48.21 | — | — | |
| E2E-MFDModality=RGB+IR2024.03 | 77.4 | 90.3 | 79.3 | 64.6 | 89.8 | 63.1 | — | — | — | — | — | |
| YOLOv8nVisible=false, Infrared=true2025.12 | 77.4 | 97.7 | 75.5 | 61.2 | 94.7 | 57.6 | — | — | — | — | — | |
| DMMMode=RGB+IR, Backbone=ResNet502026.07 | 77.2 | 90.4 | 77.8 | 63 | 88.7 | 66 | — | — | 55.8 | — | — | |
| UniDetOptimization Stage=Fine-tuning stage optimization2026.03 | 77.17 | — | — | — | — | — | — | — | 47.99 | — | — | |
| CSOM-ODAFMode=RGB+IR, Backbone=YOLOv52026.07 | 77.1 | 90.1 | 75.6 | 68.2 | 89.8 | 61.8 | — | — | 50.1 | — | — | |
| MC-DETR2026.01 | 76.9 | 94.8 | 76.7 | 60.4 | 91.1 | 61.4 | — | — | — | — | — | |
| SLBAF-NetMode=RGB+IR, Backbone=YOLOv52026.07 | 76.8 | 90.2 | 76 | 68.2 | 89.9 | 59.9 | — | — | 49.5 | — | — | |
| M2FNetMode=RGB+IR, Backbone=YOLOv82026.07 | 76.8 | 95.8 | 75.9 | 59.8 | 93.1 | 59.4 | — | — | 50.4 | — | — | |
| AFFCM2026.01 | 76.6 | 90.2 | 73.4 | 64.9 | 89.9 | 64.9 | — | — | — | — | — | |
| FFODNetMode=RGB+IR, Backbone=ResNet502026.07 | 76.3 | — | — | — | — | — | — | — | 56.9 | — | — | |
| LSKNet-OBBModality=RGB+IR, fusion_source=E2E-MFD generated images2024.03 | 75.9 | 90.3 | 77 | 63.5 | 89.5 | 59 | — | — | — | — | — | |
| CALNetModality=RGB+IR2024.03 | 75.4 | 90.3 | 76.2 | 63 | 89.1 | 58.5 | — | — | — | — | — | |
| CALNetVisible=true, Infrared=true2025.12 | 75.4 | 90.3 | 76.2 | 63 | 89.1 | 58.5 | — | — | — | — | — | |
| DAAB-FFPNMode=RGB+IR, Backbone=YOLOv82026.07 | 75.2 | — | — | — | — | — | — | — | 56.3 | — | — | |
| IV-YOLOMode=RGB+IR, Backbone=YOLOv82026.07 | 74.6 | 97.2 | 65.4 | 63.1 | 94.3 | 53 | — | — | 56.8 | — | — | |
| C²Former2026.01 | 74.2 | 90.2 | 78.3 | 64.4 | 89.8 | 58.5 | — | — | — | — | — | |
| YOLOv8nVisible=true, Infrared=false2025.12 | 74.2 | 96.2 | 72.7 | 53.2 | 94.5 | 54.4 | — | — | — | — | — | |
| C2FormerVisible=true, Infrared=true2025.12 | 74.2 | 90.2 | 68.3 | 64.4 | 89.8 | 58.5 | — | — | — | — | — | |
| C²FormerParams.(M)=101.0, GFLOPs=258.32025.12 | 74.2 | — | — | — | — | — | — | — | — | — | — | |
| C2Former-S2ANetMode=RGB+IR, Backbone=ResNet502026.07 | 74.2 | 90.2 | 68.3 | 64.4 | 89.8 | 58.5 | — | — | 47.3 | — | — | |
| Simple Joint TrainingOptimization Stage=Fine-tuning stage optimization2026.03 | 73.28 | — | — | — | — | — | — | — | 44.99 | — | — | |
| CRSIODMode=RGB+IR, Backbone=YOLOv82026.07 | 73.2 | 95.6 | 71.7 | 50.5 | 92.2 | 55.8 | — | — | 50.8 | — | — | |
| TSFADet2026.01 | 73.1 | 89.9 | 67.9 | 63.7 | 89.8 | 54 | — | — | — | — | — | |
| TSFADetMode=RGB+IR, Backbone=ResNet502026.07 | 73.1 | 89.9 | 67.9 | 63.7 | 89.8 | 54 | — | — | 44.1 | — | — | |
| LSKNet-OBBModality=IR2024.03 | 72.8 | 90.3 | 73.3 | 57.8 | 89.2 | 53.2 | — | — | — | — | — | |
| multimodal DINOMode=RGB+IR, Backbone=YOLOv52026.07 | 72.5 | 89.5 | 75.4 | 54.3 | 88.8 | 54.3 | — | — | 50.3 | — | — | |
| MBNet2026.01 | 71.9 | 90.1 | 64.4 | 62.4 | 88.8 | 53.6 | — | — | — | — | — | |
| Dual-YOLOMode=RGB+IR, Backbone=YOLOv72026.07 | 71.9 | 95.9 | 69.7 | 55.9 | 91.6 | 46.6 | — | — | 55.2 | — | — | |
| YOLOv8l-IRMode=IR, Backbone=YOLOv82026.07 | 71.9 | 93.4 | 69.3 | 53.7 | 91.9 | 51.1 | — | — | 49.1 | — | — | |
| LF-MDetVisible=true, Infrared=true2025.12 | 71.8 | 82.2 | 73.6 | 59.6 | 86.6 | 57 | — | — | — | — | — | |
| LF-MDetParams.(M)=38.7, GFLOPs=77.72025.12 | 71.8 | — | — | — | — | — | — | — | — | — | — | |
| LF-MDetMode=RGB+IR, Backbone=ResNet502026.07 | 71.8 | — | — | — | — | — | — | — | 51.3 | — | — | |
| LSKNet-OBBModality=RGB2024.03 | 71.5 | 89.5 | 70 | 51.8 | 89.4 | 56.9 | — | — | — | — | — | |
| GLFNetMode=RGB+IR, Backbone=ResNet502026.07 | 71.4 | 90.3 | 72.7 | 53.6 | 88 | 52.6 | — | — | 54.8 | — | — | |
| YOLOv5s-OBBModality=RGB+IR, fusion_source=E2E-MFD generated images2024.03 | 70.7 | 96.7 | 69.9 | 49.9 | 92.6 | 44.5 | — | — | — | — | — | |
| TSFADetModality=RGB+IR2024.03 | 70.4 | 89.2 | 72 | 54.2 | 88.1 | 48.8 | — | — | — | — | — | |
| RoI TransformerVisible=false, Infrared=true2025.12 | 70.3 | 90.1 | 60.4 | 58.9 | 89.7 | 52.2 | — | — | — | — | — | |
| YOLOv8l-RGBMode=RGB, Backbone=YOLOv82026.07 | 70.2 | 92.5 | 68.8 | 47.8 | 91.7 | 50.2 | — | — | 48.6 | — | — | |
| Halfway Fusion2026.01 | 70 | 90.1 | 62.3 | 58.5 | 89.1 | 49.8 | — | — | — | — | — | |
| CAFN-IAMode=RGB+IR, Backbone=YOLOv52026.07 | 69.3 | 89.1 | 62 | 57.3 | 90.8 | 47.1 | — | — | 56.1 | — | — | |
| Oriented R-CNNVisible=false, Infrared=true2025.12 | 67 | 89.8 | 57.4 | 53.1 | 89.3 | 45.4 | — | — | — | — | — | |
| YOLOv5s-OBBModality=IR2024.03 | 65 | 95.6 | 57.2 | 47.5 | 89.4 | 35.2 | — | — | — | — | — | |
| S2A-NetVisible=false, Infrared=true2025.12 | 64.8 | 89.7 | 51 | 50.2 | 89 | 44 | — | — | — | — | — | |
| S²A-NetParams.(M)=38.6, GFLOPs=93.02025.12 | 64.8 | — | — | — | — | — | — | — | — | — | — | |
| YOLOFIVMode=RGB+IR, Backbone=YOLOv82026.07 | 64.7 | 95.9 | 64.2 | 34.6 | 91.6 | 37.3 | — | — | 53.1 | — | — | |
| UA-CMDetModality=RGB+IR2024.03 | 64 | 87.5 | 60.7 | 46.8 | 87.1 | 38 | — | — | — | — | — | |
| UA-CMDetVisible=true, Infrared=true2025.12 | 64 | 87.5 | 60.7 | 46.8 | 87.1 | 38 | — | — | — | — | — | |
| UA-CMDetParams.(M)=138.72025.12 | 64 | — | — | — | — | — | — | — | — | — | — | |
| Ours-s (YOLOv8s)Modality=RGB+IR, Backbone=YOLOv8s, Params (M)=37.6, GFLOPs (G)=68.7, FPS (Hz)=225.0, GPU-H (h)=7.412026.01 | 63.4 | 98.5 | 77 | 71.8 | 82.3 | 97.5 | 85.4 | 75.7 | — | — | — | |
| COMOModality=RGB+IR, Backbone=YOLOv8s, Params (M)=24.3, GFLOPs (G)=47.0, FPS (Hz)=226.5, GPU-H (h)=5.252026.01 | 63.3 | 98.1 | 75.8 | 69.4 | 80.8 | 95.4 | 83.9 | 75.1 | — | — | — | |
| Gliding VertexModality=IR2024.03 | 62.9 | 89.2 | 59.7 | 43 | 78.8 | 43.9 | — | — | — | — | — | |
| Ours-n (YOLOv8n)Modality=RGB+IR, Backbone=YOLOv8n, Params (M)=10.5, GFLOPs (G)=21.0, FPS (Hz)=237.4, GPU-H (h)=5.452026.01 | 62.1 | 98.3 | 76.2 | 69.5 | 80.7 | 96.5 | 84.2 | 74.7 | — | — | — | |
| RoI TransformerVisible=true, Infrared=false2025.12 | 61.6 | 61.6 | 55.1 | 42.3 | 85.5 | 44.8 | — | — | — | — | — | |
| CFTModality=RGB+IR, Backbone=YOLOv5s, Params (M)=11.2, GFLOPs (G)=27.5, FPS (Hz)=207.4, GPU-H (h)=3.672026.01 | 61.3 | 98.5 | 74.6 | 69.7 | 79.6 | 96.9 | 83.9 | 73.5 | — | — | — | |
| Oriented R-CNNVisible=true, Infrared=false2025.12 | 60.8 | 80.1 | 53.8 | 41.6 | 85.4 | 43.3 | — | — | — | — | — | |
| ICAFusionModality=RGB+IR, Backbone=YOLOv5s, Params (M)=23.3, GFLOPs (G)=30.1, FPS (Hz)=101.1, GPU-H (h)=14.502026.01 | 60.5 | 98.2 | 72.1 | 67.1 | 79.5 | 96.5 | 82.7 | 72.7 | — | — | — | |
| YOLOv5s-OBBModality=RGB2024.03 | 60.4 | 89 | 53.6 | 41.9 | 84.8 | 32.6 | — | — | — | — | — | |
| Ours-s (YOLOv13s)Modality=RGB+IR, Backbone=YOLOv13s, Params (M)=36.8, GFLOPs (G)=40.5, FPS (Hz)=147.5, GPU-H (h)=15.452026.01 | 60.1 | 98.3 | 70.5 | 68.8 | 74.3 | 96.6 | 81.7 | 72.3 | — | — | — | |
| Ours-n (YOLOv13n)Modality=RGB+IR, Backbone=YOLOv13n, Params (M)=9.5, GFLOPs (G)=11.5, FPS (Hz)=212.5, GPU-H (h)=7.262026.01 | 59.3 | 98.3 | 69.2 | 67.5 | 73.5 | 96.1 | 81 | 71.3 | — | — | — | |
| GHOSTModality=RGB+IR, Backbone=YOLOv5s, Params (M)=7.10, GFLOPs (G)=20.5, FPS (Hz)=165.8, GPU-H (h)=10.422026.01 | 59.1 | 97.2 | 75.6 | 66.5 | 70.9 | 95.8 | 81.2 | 72.7 | — | — | — | |
| SuperYOLOModality=RGB+IR, Backbone=YOLOv5s, Params (M)=4.85, GFLOPs (G)=18.0, FPS (Hz)=122.9, GPU-H (h)=7.242026.01 | 58.6 | 97.8 | 78.9 | 67.4 | 66.5 | 96.5 | 81.4 | 70.1 | — | — | — | |
| GM-DETRModality=RGB+IR, Backbone=RT-DETR, Params (M)=69.8, GFLOPs (G)=172.8, FPS (Hz)=80.7, GPU-H (h)=13.252026.01 | 57.8 | 92.3 | 74.9 | 65.7 | 81 | 91.2 | 81 | 70.9 | — | — | — | |
| S2A-NetVisible=true, Infrared=false2025.12 | 57.3 | 79.9 | 50 | 36.2 | 82.8 | 37.5 | — | — | — | — | — | |
| Faster R-CNN-OBBModality=IR2024.03 | 54.6 | 88.6 | 42.5 | 35.2 | 77.9 | 28.5 | — | — | — | — | — | |
| Gliding VertexModality=RGB2024.03 | 52.5 | 75.8 | 46.1 | 33.8 | 68.1 | 38.7 | — | — | — | — | — | |
| RetinaNet-OBBModality=IR2024.03 | 44.9 | 79.9 | 32.8 | 28.1 | 67.3 | 16.4 | — | — | — | — | — | |
| Faster R-CNN-OBBModality=RGB2024.03 | 44.6 | 67.9 | 38.6 | 26.3 | 67 | 23.2 | — | — | — | — | — | |
| RetinaNet-OBBModality=RGB2024.03 | 38.1 | 67.5 | 28.2 | 13.7 | 62.1 | 19.3 | — | — | — | — | — | |
| CDDFuse2025.07 | — | — | — | — | — | — | 6.5 | — | — | 80 | 7 | |
| DIDFuse2025.07 | — | — | — | — | — | — | 7.2 | — | — | 73.8 | 7.7 | |
| EMMA2025.07 | — | — | — | — | — | — | 8.7 | — | — | 70.8 | 8.7 | |
| Hy-CycleAlign2025.07 | — | — | — | — | — | — | 13.7 | — | — | 81.5 | 12.3 |