Object Detection on DOTA v1.0
82.75Overall mAPStrip R-CNN-S
Evaluation results
| Method | Links | |||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Strip R-CNN-SScale Strategy=Multi-Scale, Pre-train=IN, Parameters=30.5M, FLOPs=159G, Ensemble=true2025.01 | 82.75 | — | — | — | 88.99 | 86.56 | 61.35 | 83.94 | 81.7 | 85.16 | 88.57 | 90.88 | 88.62 | 87.36 | 75.13 | 74.34 | 84.58 | 81.49 | 82.56 | |
| Strip R-CNN-SScale Strategy=Multi-Scale, Pre-train=IN, Parameters=30.5M, FLOPs=159G2025.01 | 82.28 | — | — | — | 89.17 | 85.57 | 62.4 | 83.71 | 81.93 | 86.58 | 88.84 | 90.86 | 87.97 | 87.91 | 72.07 | 71.88 | 79.25 | 82.45 | 82.82 | |
| LSKNet-SScale Strategy=Multi-Scale, Pre-train=IN, Parameters=31.0M, FLOPs=161G2025.01 | 81.64 | — | — | — | 89.57 | 86.34 | 63.13 | 83.67 | 82.2 | 86.1 | 88.66 | 90.89 | 88.41 | 87.42 | 71.72 | 69.58 | 78.88 | 81.77 | 76.52 | |
| Strip R-CNN-TScale Strategy=Multi-Scale, Pre-train=IN, Parameters=20.5M, FLOPs=123G2025.01 | 81.4 | — | — | — | 89.14 | 84.9 | 61.78 | 83.5 | 81.54 | 85.87 | 88.64 | 90.89 | 88.02 | 87.31 | 71.55 | 70.74 | 78.66 | 79.81 | 78.16 | |
| RTMDet-RScale Strategy=Multi-Scale, Pre-train=CO, Parameters=52.3M, FLOPs=205G2025.01 | 81.33 | — | — | — | 88.01 | 86.17 | 58.54 | 82.44 | 81.3 | 84.82 | 88.71 | 90.89 | 88.77 | 87.37 | 71.96 | 71.18 | 81.23 | 81.4 | 77.13 | |
| RVSAScale Strategy=Multi-Scale, Pre-train=MA, Parameters=114.4M, FLOPs=414G2025.01 | 81.24 | — | — | — | 88.97 | 85.76 | 61.46 | 81.27 | 79.98 | 85.31 | 88.3 | 90.84 | 85.06 | 87.5 | 66.77 | 73.11 | 84.75 | 81.88 | 77.58 | |
| PKINet-SScale Strategy=Multi-Scale, Pre-train=IN, Parameters=30.8M, FLOPs=190G2025.01 | 81.06 | — | — | — | 89.02 | 86.73 | 58.95 | 81.2 | 80.41 | 84.94 | 88.1 | 90.88 | 86.6 | 87.28 | 67.1 | 74.81 | 78.18 | 81.91 | 70.62 | |
| KFloUScale Strategy=Multi-Scale, Pre-train=IN, Parameters=58.8M, FLOPs=206G2025.01 | 80.93 | — | — | — | 89.44 | 84.41 | 62.22 | 82.51 | 80.1 | 86.07 | 88.68 | 90.9 | 87.32 | 88.38 | 72.8 | 71.95 | 78.96 | 74.95 | 75.27 | |
| AOPGScale Strategy=Multi-Scale, Pre-train=IN2025.01 | 80.66 | — | — | — | 89.88 | 85.57 | 60.9 | 81.51 | 78.7 | 85.29 | 88.85 | 90.89 | 87.6 | 87.65 | 71.66 | 68.69 | 82.31 | 77.32 | 73.1 | |
| DODetScale Strategy=Multi-Scale, Pre-train=IN2025.01 | 80.62 | — | — | — | 89.96 | 85.52 | 58.01 | 81.22 | 78.71 | 85.46 | 88.59 | 90.89 | 87.12 | 87.8 | 70.5 | 71.54 | 82.06 | 77.43 | 74.47 | |
| PKINet-v2-SBackbone=PKINet-v2-S, FPS=54.60, #P=30.7M, FLOPs=173G, Pre-trained=ImageNet-1K, Framework=Oriented RCNN, Hardware=NVIDIA A100-40G2026.03 | 80.46 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Strip R-CNN-SScale Strategy=Single-Scale, Pre-train=IN, Parameters=30.5M, FLOPs=159G2025.01 | 80.06 | — | — | — | 88.91 | 86.38 | 57.44 | 76.37 | 79.73 | 84.38 | 88.25 | 90.86 | 86.71 | 87.45 | 69.89 | 66.82 | 79.25 | 82.91 | 75.58 | |
| StripNet-SBackbone=StripNet-S, FPS=46.40, #P=30.5M, FLOPs=172G, Pre-trained=ImageNet-1K, Framework=Oriented RCNN, Hardware=NVIDIA A100-40G2026.03 | 79.85 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LWGANet-L2Backbone=LWGANet-L2, FPS=33.50, #P=29.2M, FLOPs=159G, Pre-trained=ImageNet-1K, Framework=Oriented RCNN, Hardware=NVIDIA A100-40G2026.03 | 79.02 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RTMDet-RScale Strategy=Single-Scale, Pre-train=IN, Parameters=52.3M, FLOPs=205G2025.01 | 78.85 | — | — | — | 89.43 | 84.21 | 55.2 | 75.06 | 80.81 | 84.53 | 88.97 | 90.9 | 87.38 | 87.25 | 63.09 | 67.87 | 78.09 | 80.78 | 69.13 | |
| PKINet-SScale Strategy=Single-Scale, Pre-train=IN, Parameters=30.8M, FLOPs=190G2025.01 | 78.39 | — | — | — | 89.72 | 84.2 | 55.81 | 77.63 | 80.25 | 84.45 | 88.12 | 90.88 | 87.57 | 86.07 | 66.86 | 70.23 | 77.47 | 73.62 | 62.94 | |
| PKINet-v1-SBackbone=PKINet-v1-S, FPS=14.05, #P=30.8M, FLOPs=184G, Pre-trained=ImageNet-1K, Framework=Oriented RCNN, Hardware=NVIDIA A100-40G2026.03 | 78.39 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LSKNet-SScale Strategy=Single-Scale, Pre-train=IN, Parameters=31.0M, FLOPs=161G2025.01 | 77.49 | — | — | — | 89.66 | 85.52 | 57.72 | 75.7 | 74.95 | 78.69 | 88.24 | 90.88 | 86.79 | 86.38 | 66.92 | 63.77 | 77.77 | 74.47 | 64.82 | |
| LSKNet-SBackbone=LSKNet-S, FPS=51.00, #P=31.0M, FLOPs=161G, Pre-trained=ImageNet-1K, Framework=Oriented RCNN, Hardware=NVIDIA A100-40G2026.03 | 77.49 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| R3Det-KLDScale Strategy=Single-Scale, Pre-train=IN, Parameters=41.9M, FLOPs=336G2025.01 | 77.36 | — | — | — | 88.9 | 84.17 | 55.8 | 69.35 | 78.72 | 84.08 | 87 | 89.75 | 84.32 | 85.73 | 64.74 | 61.8 | 76.62 | 78.49 | 70.89 | |
| ARCScale Strategy=Single-Scale, Pre-train=IN, Parameters=74.4M, FLOPs=217G2025.01 | 77.35 | — | — | — | 89.4 | 82.48 | 55.33 | 73.88 | 79.37 | 84.05 | 88.06 | 90.9 | 86.44 | 84.83 | 63.63 | 70.32 | 74.29 | 71.91 | 65.43 | |
| COBBScale Strategy=Single-Scale, Pre-train=IN, Parameters=41.9M2025.01 | 76.52 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| R3Det-GWDScale Strategy=Single-Scale, Pre-train=IN, Parameters=41.9M, FLOPs=336G2025.01 | 76.34 | — | — | — | 88.82 | 82.94 | 55.63 | 72.75 | 78.52 | 83.1 | 87.46 | 90.21 | 86.36 | 85.44 | 64.7 | 61.41 | 73.46 | 76.94 | 57.38 | |
| CSLScale Strategy=Multi-Scale, Pre-train=IN, Parameters=37.4M, FLOPs=236G2025.01 | 76.17 | — | — | — | 90.25 | 85.53 | 54.64 | 75.31 | 70.44 | 73.51 | 77.62 | 90.84 | 86.15 | 86.69 | 69.6 | 68.04 | 73.83 | 71.1 | 68.93 | |
| O-RCNNScale Strategy=Single-Scale, Pre-train=IN, Parameters=41.1M, FLOPs=199G2025.01 | 75.87 | — | — | — | 89.46 | 82.12 | 54.78 | 70.86 | 78.93 | 83 | 88.2 | 90.9 | 87.5 | 84.68 | 63.97 | 67.69 | 74.94 | 68.84 | 52.28 | |
| SASMScale Strategy=Single-Scale, Pre-train=IN, Parameters=36.6M2025.01 | 74.92 | — | — | — | 86.42 | 78.97 | 52.47 | 69.84 | 77.3 | 75.99 | 86.72 | 90.89 | 82.63 | 85.66 | 60.13 | 68.25 | 73.98 | 72.22 | 62.37 | |
| AO2-DETRScale Strategy=Single-Scale, Pre-train=IN, Parameters=74.3M, FLOPs=304G2025.01 | 72.15 | — | — | — | 86.01 | 75.92 | 46.02 | 66.65 | 79.7 | 79.93 | 89.17 | 90.44 | 81.19 | 76 | 56.91 | 62.45 | 64.22 | 65.8 | 58.96 | |
| CenterMapScale Strategy=Single-Scale, Pre-train=IN, Parameters=41.1M, FLOPs=198G2025.01 | 71.59 | — | — | — | 89.02 | 80.56 | 49.41 | 61.98 | 77.99 | 74.19 | 83.74 | 89.44 | 78.01 | 83.52 | 47.64 | 65.93 | 63.68 | 67.07 | 61.59 | |
| EMO2-DETRScale Strategy=Single-Scale, Pre-train=IN, Parameters=74.3M, FLOPs=304G2025.01 | 70.91 | — | — | — | 87.99 | 79.46 | 45.74 | 66.64 | 78.9 | 73.9 | 73.3 | 90.4 | 80.55 | 85.89 | 55.19 | 63.62 | 51.83 | 70.15 | 60.04 | |
| BPIM(YOLOv5l)Resolution=640×640, Parameters (M)=56.83, GFLOPs=155.72026.01 | — | 78.67 | — | 53.51 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| BPIM(YOLOv5n)Resolution=640×640, Parameters (M)=2.83, GFLOPs=7.12026.01 | — | 68.97 | — | 42.83 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FCOSR-LResolution=1024×1024, Parameters (M)=89.64, GFLOPs=445.72026.01 | — | 77.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Gliding Vertexbaseline=true2024.02 | — | 73.31 | 41.62 | 41.57 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Oriented R-CNNbaseline=true2024.02 | — | 75.11 | 47.48 | 45.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Oriented R-CNN + COBB-lnbackbone=Oriented R-CNN, variant=ln2024.02 | — | 76.25 | 48.48 | 45.92 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Oriented R-CNN + COBB-sigbackbone=Oriented R-CNN, variant=sig2024.02 | — | 75.52 | 48.35 | 45.61 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PP-YOLOE-R-lResolution=1024×1024, Parameters (M)=53.29, GFLOPs=281.62026.01 | — | 78.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RoI Trans.baseline=true2024.02 | — | 75.59 | 48.54 | 46.35 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RoI Trans. + COBB-ln-lnbackbone=RoI Trans., variant=ln-ln2024.02 | — | 76.53 | 50.41 | 46.97 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RoI Trans. + COBB-ln-sigbackbone=RoI Trans., variant=ln-sig2024.02 | — | 76.55 | 49.91 | 46.68 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RoI Trans. + COBB-sig-sigbackbone=RoI Trans., variant=sig-sig2024.02 | — | 76.49 | 50.26 | 46.63 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Rotated Faster R-CNNbaseline=true2024.02 | — | 73.01 | 40.13 | 41.33 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Rotated Faster R-CNN + COBB-lnbackbone=Rotated Faster R-CNN, variant=ln2024.02 | — | 74.44 | 44.08 | 43.53 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Rotated Faster R-CNN + COBB-sigbackbone=Rotated Faster R-CNN, variant=sig2024.02 | — | 74 | 44.03 | 43.29 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| YOLOv10lResolution=640×640, Parameters (M)=25.74, GFLOPs=126.42026.01 | — | 72.4 | — | 49.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| YOLOv10nResolution=640×640, Parameters (M)=2.7, GFLOPs=8.32026.01 | — | 67.7 | — | 45 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| YOLOv5l-P2Resolution=640×640, Parameters (M)=47.17, GFLOPs=127.42026.01 | — | 76.82 | — | 52.16 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| YOLOv5n-P2Resolution=640×640, Parameters (M)=1.78, GFLOPs=4.82026.01 | — | 66.7 | — | 40.42 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| YOLOv7Resolution=640×640, Parameters (M)=37.15, GFLOPs=105.12026.01 | — | 78.53 | — | 53.34 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |