Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/AerialFormer-B

AerialFormer-B

Reported on 10 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Medical5 results

Semantic SegmentationonISPRS Potsdam
Mean F1· 2023-06-12
94.1
best: 94.7 (D2LS)
SOTA
AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation arXiv:2306.06842
Semantic SegmentationonISPRS Potsdam
Mean IoU· 2023-06-12
89.1
best: 89.45 (U-Net (ConvFormer-M36))
SOTA
AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation arXiv:2306.06842
Semantic SegmentationonISPRS Potsdam
Overall Accuracy· 2023-06-12
93.9
SOTA
AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation arXiv:2306.06842
Semantic SegmentationonLoveDA
Category mIoU· 2023-06-12
54.1
best: 56.16 (U-Net (MaxViT-S))
AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation arXiv:2306.06842
Semantic SegmentationoniSAID
mIoU· 2023-06-12
69.3
best: 70.3 (SegNeXt-L)
AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation arXiv:2306.06842

Audio5 results

10-shot image generationonISPRS Potsdam
Mean F1· 2023-06-12
94.1
best: 94.7 (D2LS)
SOTA
AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation arXiv:2306.06842
10-shot image generationonISPRS Potsdam
Mean IoU· 2023-06-12
89.1
best: 89.45 (U-Net (ConvFormer-M36))
SOTA
AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation arXiv:2306.06842
10-shot image generationonISPRS Potsdam
Overall Accuracy· 2023-06-12
93.9
SOTA
AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation arXiv:2306.06842
10-shot image generationonLoveDA
Category mIoU· 2023-06-12
54.1
best: 56.16 (U-Net (MaxViT-S))
AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation arXiv:2306.06842
10-shot image generationoniSAID
mIoU· 2023-06-12
69.3
best: 70.3 (SegNeXt-L)
AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation arXiv:2306.06842