Long Tail Learning With Class Descriptors On 3
Metrics
Per-Class Accuracy
Results
Performance results of various models on this benchmark
Model Name | Per-Class Accuracy | Paper Title | Repository |
|---|---|---|---|
| OLTR | 37.7 | Large-Scale Long-Tailed Recognition in an Open World | |
| DRAGON + Bal'Loss | 53.5 | From Generalized zero-shot learning to long-tail with class descriptors | |
| DRAGON | 51.2 | From Generalized zero-shot learning to long-tail with class descriptors | |
| LWS | 49.9 | Decoupling Representation and Classifier for Long-Tailed Recognition | |
| CADA-VAE | 49.3 | Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders |
0 of 5 row(s) selected.