Long Tail Learning With Class Descriptors On
评估指标
Long-Tailed Accuracy
Per-Class Accuracy
评测结果
各个模型在此基准测试上的表现结果
模型名称 | Long-Tailed Accuracy | Per-Class Accuracy | Paper Title | Repository |
|---|---|---|---|---|
| LWS | 65.7 | 53.1 | Decoupling Representation and Classifier for Long-Tailed Recognition | - |
| DRAGON + Bal'Loss | 66.5 | 60.1 | From Generalized zero-shot learning to long-tail with class descriptors | - |
| LDAM | 64.1 | 50.1 | Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss | - |
| CADA-VAE | 57.4 | 48.3 | Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders | |
| DRAGON | 67.7 | 57.8 | From Generalized zero-shot learning to long-tail with class descriptors | - |
0 of 5 row(s) selected.