Test Accuracy: 95.9
Papers with Code · CC BY-SA 4.0
Learning with noisy labels
Learning with noisy labels means When we say "noisy labels," we mean that an adversary has intentionally messed up the labels, which would have come from a "clean" distribution otherwise. This setting can also be used to cast learning from only positive and unlabeled data.
논문
Accuracy (mean): 94.20
Accuracy (mean): 94.88
Accuracy (mean): 86.28
Accuracy (mean): 87.71
mIOU: 25.5
Test Accuracy: 43.82
Accuracy (mean): 90.75
Accuracy (mean): 90.30
Accuracy (mean): 90.21
Accuracy (mean): 90.90
Accuracy (mean): 89.35
Accuracy (mean): 87.70
ACCURACY: 83.4
Accuracy (mean): 89.47
Accuracy (mean): 95.04
Test Accuracy: 51.2
Accuracy (mean): 91.42
Accuracy (mean): 88.76
Accuracy (mean): 88.27
Accuracy (mean): 96.21
Accuracy (mean): 95.31
Accuracy (mean): 90.37
Accuracy (mean): 89.79