UPS

Reported on 2 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.

Methodology1 result

ClassificationonChest X-Ray14 2% labeled
AUC· 2021-01-15
65.51
best: 74.82 (ACPL)
SOTA
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning arXiv:2101.06329

Medical1 result

Medical Image ClassificationonChest X-Ray14 2% labeled
AUC· 2021-01-15
65.51
best: 74.82 (ACPL)
SOTA
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning arXiv:2101.06329