Triple-GAN-V2 (ResNet-26)

Reported on 4 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 Vision4 results

Image ClassificationonCIFAR-10, 4000 Labels
Percentage error· 2019-12-20
6.54
best: 3.96 (SimMatch)
Triple Generative Adversarial Networks arXiv:1912.09784
Image ClassificationonCIFAR-10, 1000 Labels
Accuracy· 2019-12-20
91.59
best: 92.25 (MixMatch)
Triple Generative Adversarial Networks arXiv:1912.09784
Semi-Supervised Image ClassificationonCIFAR-10, 4000 Labels
Percentage error· 2019-12-20
6.54
best: 3.96 (SimMatch)
Triple Generative Adversarial Networks arXiv:1912.09784
Semi-Supervised Image ClassificationonCIFAR-10, 1000 Labels
Accuracy· 2019-12-20
91.59
best: 92.25 (MixMatch)
Triple Generative Adversarial Networks arXiv:1912.09784