FixMatch (CTA)

Reported on 3 benchmarks across 2 tasks · 1 paper

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

Computer Vision3 results

Image ClassificationonSTL-10
Percentage correct· 2020-01-21
94.83
best: 99.64 (µ2Net+ (ViT-L/16))
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence arXiv:2001.07685
Image ClassificationonCIFAR-10, 4000 Labels
Percentage error· 2020-01-21
4.31
best: 3.96 (SimMatch)
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence arXiv:2001.07685
Semi-Supervised Image ClassificationonCIFAR-10, 4000 Labels
Percentage error· 2020-01-21
4.31
best: 3.96 (SimMatch)
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence arXiv:2001.07685