Balanced Softmax + CMO

Reported on 5 benchmarks across 5 tasks · 1 paper

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

Methodology3 results

Generalized Few-Shot ClassificationonCIFAR-100-LT (ρ=100)
Error Rate· 2021-12-01
53.4
best: 10.9 (LPT)
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification arXiv:2112.00412
Long-tail LearningonCIFAR-100-LT (ρ=100)
Error Rate· 2021-12-01
53.4
best: 10.9 (LPT)
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification arXiv:2112.00412
Generalized Few-Shot LearningonCIFAR-100-LT (ρ=100)
Error Rate· 2021-12-01
53.4
best: 10.9 (LPT)
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification arXiv:2112.00412

Computer Vision2 results

Image ClassificationonCIFAR-100-LT (ρ=100)
Error Rate· 2021-12-01
53.4
best: 10.9 (LPT)
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification arXiv:2112.00412
Few-Shot Image ClassificationonCIFAR-100-LT (ρ=100)
Error Rate· 2021-12-01
53.4
best: 10.9 (LPT)
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification arXiv:2112.00412