| object-detection-in-aerial-images-on-dior-r | ViTAE-B + RVSA-ORCN | #4 | mAP: 71.05 |
| object-detection-in-aerial-images-on-dior-r | ViT-B + RVSA-ORCN | #5 | mAP: 70.85 |
| object-detection-in-aerial-images-on-dota | ViTAE-B + RVSA-ORCN | #11 | mAP: 81.24% |
| object-detection-in-aerial-images-on-dota | ViT-B + RVSA-ORCN | #13 | mAP: 81.01% |
| semantic-segmentation-on-isaid | ViTAE-B + RVSA-UperNet | #13 | mIoU: 64.49 |
| semantic-segmentation-on-isaid | ViT-B + RVSA-UperNet | #16 | mIoU: 63.85 |
| semantic-segmentation-on-isprs-potsdam | ViTAE-B + RVSA -UperNet | #9 | Overall Accuracy: 91.22 |
| semantic-segmentation-on-isprs-potsdam | ViT-B + RVSA-UperNet | #13 | Overall Accuracy: 90.77 |
| semantic-segmentation-on-loveda | ViTAE-B + RVSA-UperNet | #12 | Category mIoU: 52.44 |
| semantic-segmentation-on-loveda | ViT-B + RVSA-UperNet | #15 | Category mIoU: 51.95 |