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 | 66.19 | — | Unverified |
| 2 | CLIP(ViT-B/16) | Average mAP | 60.17 | — | Unverified |
| 3 | LMPT(ResNet-50) | Average mAP | 58.97 | — | Unverified |
| 4 | LTML(ResNet-50) | Average mAP | 56.9 | — | Unverified |
| 5 | CLIP(ResNet-50) | Average mAP | 56.19 | — | Unverified |
| 6 | PG Loss(ResNet-50) | Average mAP | 54.43 | — | Unverified |
| 7 | DB Focal(ResNet-50) | Average mAP | 53.55 | — | Unverified |
| 8 | Focal Loss(ResNet-50) | Average mAP | 49.46 | — | Unverified |
| 9 | CB Loss(ResNet-50) | Average mAP | 49.06 | — | Unverified |
| 10 | RS(ResNet-50) | Average mAP | 46.97 | — | Unverified |