Posterior Re-calibration for Imbalanced Datasets
Open paper
Benchmark
Model
Rank
Results
long-tail-learning-on-cifar-100-lt-r-10
CE-DRW-IC
–
Error Rate: 41.4
long-tail-learning-on-cifar-100-lt-r-100
CE-DRW-IC
–
Error Rate: 56.9
long-tail-learning-on-inaturalist-2018
CE-DRW-IC
–
Top-1 Accuracy: 67.9%
Rank counts only results with a code link.