Long Tail Learning With Class Descriptors On 2
Metrics
Long-Tailed Accuracy
Per-Class Accuracy
Results
Performance results of various models on this benchmark
Model Name | Long-Tailed Accuracy | Per-Class Accuracy | Paper Title | Repository |
|---|---|---|---|---|
| CADA-VAE | 89.5 | 73.5 | Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders | |
| DRAGON + Bal'Loss | 92.2 | 76.2 | From Generalized zero-shot learning to long-tail with class descriptors | |
| DRAGON | 94.1 | 74.1 | From Generalized zero-shot learning to long-tail with class descriptors | |
| LDAM | 93.5 | 69.1 | Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss | |
| LWS | 93.5 | 73.4 | Decoupling Representation and Classifier for Long-Tailed Recognition |
0 of 5 row(s) selected.