ViT-B + RVSA-ORCN

Reported on 5 benchmarks across 5 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology4 results

3DonDIOR-R
mAP· 2022-08-08
70.85
best: 74.54 (MAE+MTP(ViT-L+RVSA))
Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model arXiv:2208.03987
2D ClassificationonDIOR-R
mAP· 2022-08-08
70.85
best: 74.54 (MAE+MTP(ViT-L+RVSA))
Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model arXiv:2208.03987
2D Object DetectiononDIOR-R
mAP· 2022-08-08
70.85
best: 74.54 (MAE+MTP(ViT-L+RVSA))
Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model arXiv:2208.03987
16konDIOR-R
mAP· 2022-08-08
70.85
best: 74.54 (MAE+MTP(ViT-L+RVSA))
Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model arXiv:2208.03987

Computer Vision1 result

Object DetectiononDIOR-R
mAP· 2022-08-08
70.85
best: 74.54 (MAE+MTP(ViT-L+RVSA))
Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model arXiv:2208.03987