Object Detection In Aerial Images On Dior R
評価指標
mAP
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | mAP | Paper Title | Repository |
|---|---|---|---|
| ViT-G12X4 | 73.60 | A Billion-scale Foundation Model for Remote Sensing Images | - |
| MAE+MTP(ViT-L+RVSA) | 74.54 | MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining | |
| MAE+MTP(ViT-B+RVSA) | 71.29 | MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining | |
| LEGNet-S | 68.40 | - | - |
| IMP+MTP(InternImage-XL) | 72.17 | MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining | |
| DecoupleNet D2 | 67.08 | DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual Tasks | |
| ViTAE-B + RVSA-ORCN | 71.05 | Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model | |
| LWGANet L2 | 68.53 | LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks | |
| ViT-B + RVSA-ORCN | 70.85 | Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model |
0 of 9 row(s) selected.