IMP-ViTAEv2-S-UperNet

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Medical2 results

Semantic SegmentationoniSAID
mIoU· 2022-04-06
65.3
best: 70.3 (SegNeXt-L)
SOTA
An Empirical Study of Remote Sensing Pretraining arXiv:2204.02825
Semantic SegmentationonISPRS Potsdam
Overall Accuracy· uses extra data· 2022-04-06
91.6
best: 93.9 (AerialFormer-B)
An Empirical Study of Remote Sensing Pretraining arXiv:2204.02825

Audio2 results

10-shot image generationoniSAID
mIoU· 2022-04-06
65.3
best: 70.3 (SegNeXt-L)
SOTA
An Empirical Study of Remote Sensing Pretraining arXiv:2204.02825
10-shot image generationonISPRS Potsdam
Overall Accuracy· uses extra data· 2022-04-06
91.6
best: 93.9 (AerialFormer-B)
An Empirical Study of Remote Sensing Pretraining arXiv:2204.02825