RelationMatch

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 ClassificationonSTL-10, 40 Labels
Accuracy· 2023-05-17
86.06
best: 95.43 (SemiOccam)
SOTA
RelationMatch: Matching In-batch Relationships for Semi-supervised Learning arXiv:2305.10397
Semi-Supervised Image ClassificationonSTL-10, 40 Labels
Accuracy· 2023-05-17
86.06
best: 95.43 (SemiOccam)
SOTA
RelationMatch: Matching In-batch Relationships for Semi-supervised Learning arXiv:2305.10397
Image ClassificationonCIFAR-10, 40 Labels
Percentage error· 2023-05-17
4.96
best: 3.51 (SemiOccam)
RelationMatch: Matching In-batch Relationships for Semi-supervised Learning arXiv:2305.10397
Semi-Supervised Image ClassificationonCIFAR-10, 40 Labels
Percentage error· 2023-05-17
4.96
best: 3.51 (SemiOccam)
RelationMatch: Matching In-batch Relationships for Semi-supervised Learning arXiv:2305.10397