FarSeg++@Swin-T

Reported on 4 benchmarks across 4 tasks

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

Medical1 result

Semantic SegmentationoniSAID
mIoU
66.3
best: 70.3 (SegNeXt-L)

Methodology1 result

Remote SensingonUV6K
IoU (%)
65.8
best: 66.4 (FarSeg++@MiT-B2)

Computer Vision1 result

The Semantic Segmentation Of Remote Sensing ImageryonUV6K
IoU (%)
65.8
best: 66.4 (FarSeg++@MiT-B2)

Audio1 result

10-shot image generationoniSAID
mIoU
66.3
best: 70.3 (SegNeXt-L)