Object Detection on DIOR (mAP)
34.25mAPcenter-periphery attention refinement framework
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| center-periphery attention refinement frameworkBackbone=Swin-T, Shots=102026.03 | 34.25 | — | |
| CD-ViTO*Backbone=Swin-T, Venue=ECCV’24, Shots=102026.03 | 31.15 | — | |
| GLIPBackbone=Swin-T, Venue=CVPR’22, Shots=102026.03 | 31.1 | — | |
| CD-ViTO†Backbone=ViT-L/14, Venue=ECCV’24, Shots=102026.03 | 30.8 | — | |
| VFM-MoE*Backbone=Swin-T, Venue=NIPS’25, Shots=102026.03 | 30.67 | — | |
| ViTDet*Backbone=Swin-T, Venue=ECCV’22, Shots=102026.03 | 30.1 | — | |
| ViTDet†Backbone=ViT-B/14, Venue=ECCV’22, Shots=102026.03 | 29.4 | — | |
| Domain-RAG*Backbone=Swin-T, Venue=NIPS’25, Shots=102026.03 | 29.23 | — | |
| DE-ViT*Backbone=Swin-T, Venue=arXiv’23, Shots=102026.03 | 26.8 | — | |
| Distill†Backbone=ResNet50, Venue=ICASSP’23, Shots=102026.03 | 26.5 | — | |
| DE-ViT†Backbone=ViT-L/14, Venue=arXiv’23, Shots=102026.03 | 25.6 | — | |
| Detic*Backbone=Swin-T, Venue=ECCV’22, Shots=102026.03 | 17.2 | — | |
| Detic†Backbone=ViT-L/14, Venue=ECCV’22, Shots=102026.03 | 15.4 | — | |
| GeoSANEBackbone=Swin-B2026.03 | — | 79 | |
| RingMoBackbone=Swin-B2026.03 | — | 75.9 | |
| SatMAEBackbone=ViT-L2026.03 | — | 70.9 | |
| Scale-MAEBackbone=ViT-L2026.03 | — | 73.8 | |
| SkySenseBackbone=ViT-L2026.03 | — | 78.7 |