Long-tail Learning
Long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing models from a large number of images that follow a long-tailed class distribution.
Papers
Showing 1–10 of 131 papers
All datasetsImageNet-LTCIFAR-100-LT (ρ=100)CIFAR-10-LT (ρ=10)iNaturalist 2018CIFAR-100-LT (ρ=10)Places-LTCIFAR-10-LT (ρ=100)CIFAR-100-LT (ρ=50)MIMIC-CXR-LTNIH-CXR-LTCOCO-MLTVOC-MLT
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | LMPT(ViT-B/16) | Average mAP | 87.88 | — | Unverified |
| 2 | LMPT(ResNet-50) | Average mAP | 85.44 | — | Unverified |
| 3 | LTML(ResNet-50) | Average mAP | 81.44 | — | Unverified |
| 4 | PG Loss(ResNet-50) | Average mAP | 80.37 | — | Unverified |
| 5 | DB Focal(ResNet-50) | Average mAP | 78.94 | — | Unverified |
| 6 | RS(ResNet-50) | Average mAP | 75.38 | — | Unverified |
| 7 | CB Focal(ResNet-50) | Average mAP | 75.24 | — | Unverified |
| 8 | Focal Loss(ResNet-50) | Average mAP | 73.88 | — | Unverified |
| 9 | OLTR(ResNet-50) | Average mAP | 71.02 | — | Unverified |
| 10 | LDAM(ResNet-50) | Average mAP | 70.73 | — | Unverified |