ICT (WRN-28-2)

Reported on 4 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.

Computer Vision4 results

Image ClassificationonSVHN, 1000 labels
Accuracy· 2019-03-09
96.47
best: 97.58 (EnAET)
SOTA
Interpolation Consistency Training for Semi-Supervised Learning arXiv:1903.03825
Semi-Supervised Image ClassificationonSVHN, 1000 labels
Accuracy· 2019-03-09
96.47
best: 97.58 (EnAET)
SOTA
Interpolation Consistency Training for Semi-Supervised Learning arXiv:1903.03825
Image ClassificationonCIFAR-10, 4000 Labels
Percentage error· 2019-03-09
7.66
best: 3.96 (SimMatch)
Interpolation Consistency Training for Semi-Supervised Learning arXiv:1903.03825
Semi-Supervised Image ClassificationonCIFAR-10, 4000 Labels
Percentage error· 2019-03-09
7.66
best: 3.96 (SimMatch)
Interpolation Consistency Training for Semi-Supervised Learning arXiv:1903.03825