FeatMatch

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Computer Vision4 results

Image ClassificationonMini-ImageNet, 10000 Labels
Accuracy· 2020-07-16
65.21
SOTA
FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning arXiv:2007.08505
Image ClassificationonMini-ImageNet, 4000 Labels
Accuracy· 2020-07-16
60.95
best: 66.55 (SimPLE)
SOTA
FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning arXiv:2007.08505
Semi-Supervised Image ClassificationonMini-ImageNet, 10000 Labels
Accuracy· 2020-07-16
65.21
SOTA
FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning arXiv:2007.08505
Semi-Supervised Image ClassificationonMini-ImageNet, 4000 Labels
Accuracy· 2020-07-16
60.95
best: 66.55 (SimPLE)
SOTA
FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning arXiv:2007.08505