DeepLabv3+‐Xception‐65

Reported on 4 benchmarks across 2 tasks

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

Medical2 results

Semantic SegmentationonOkutama Drone and Swiss Drone Dataset
Acc
90.72
best: 90.78 (DeepLabv3+‐ResNet‐101)
Semantic SegmentationonOkutama Drone and Swiss Drone Dataset
mIoU
64.34
best: 65.88 (DeepLabv3+‐ResNet‐101)

Audio2 results

10-shot image generationonOkutama Drone and Swiss Drone Dataset
Acc
90.72
best: 90.78 (DeepLabv3+‐ResNet‐101)
10-shot image generationonOkutama Drone and Swiss Drone Dataset
mIoU
64.34
best: 65.88 (DeepLabv3+‐ResNet‐101)