Image Classification on CIFAR-10 LT (Accuracy by Sampling Ratio)
91.24Acc (Ratio 10)Dynamic Loss
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Dynamic LossBackbone=ResNet322022.11 | 91.24 | 88.3 | 86.46 | 82.95 | 87.24 | |
| Dynamic Loss + Logit AdjustmentBackbone=ResNet322022.11 | 91.1 | 89.54 | 85.52 | 83.43 | 87.4 | |
| Balanced-SoftmaxBackbone=ResNet322022.11 | 91.01 | 88.85 | 86.44 | 82.31 | 87.15 | |
| Dynamic Loss + Balanced-SoftmaxBackbone=ResNet322022.11 | 90.99 | 89.66 | 85.49 | 83.21 | 87.34 | |
| MiSLASBackbone=ResNet322022.11 | 90 | 88.52 | 85.7 | 82.1 | 86.58 | |
| WDBackbone=ResNet322022.11 | 89.8 | 84.81 | 79.66 | 74.84 | 82.28 | |
| Logit AdjustmentBackbone=ResNet322022.11 | 89.64 | 86.77 | 82.61 | 78.38 | 84.35 | |
| FaMUSBackbone=ResNet322022.11 | 87.9 | 86.24 | 83.32 | 80.96 | 84.61 | |
| LDAM-DRWBackbone=ResNet322022.11 | 87.68 | 85.51 | 81.64 | 78.02 | 83.21 | |
| CB FocalBackbone=ResNet322022.11 | 87.49 | 84.36 | 79.27 | 74.57 | 81.42 | |
| Focal LossBackbone=ResNet322022.11 | 86.66 | 82.76 | 76.71 | 70.38 | 79.13 | |
| Cross entropyBackbone=ResNet322022.11 | 86.39 | 82.23 | 74.81 | 70.36 | 78.45 | |
| CMOBackbone=ResNet322022.11 | 83.26 | 89.27 | 87.19 | 85.35 | 86.27 |