Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

Open paper
Benchmark Model Rank Results
long-tail-learning-on-cifar-10-lt-r-10LDAM-DRW#32Error Rate: 11.84
long-tail-learning-on-cifar-10-lt-r-10Class-balanced Resampling#39Error Rate: 13.21
long-tail-learning-on-cifar-10-lt-r-10Empirical Risk Minimization (ERM, CE)#41Error Rate: 13.61
long-tail-learning-on-cifar-10-lt-r-100LDAM-DRW#25Error Rate: 22.97
long-tail-learning-on-cifar-100-lt-r-10LDAM-DRW#25Error Rate: 41.29
long-tail-learning-on-cifar-100-lt-r-100LDAM-DRW#52Error Rate: 57.96
long-tail-learning-on-coco-mltLDAM(ResNet-50)#11Average mAP: 40.53
long-tail-learning-on-voc-mltLDAM(ResNet-50)#10Average mAP: 70.73

Rank counts only results with a code link.