Image Classification on Fashion-MNIST class-prior shift ρ=100, μ=0.5 (test)
74.25AccuracyADIW-KL
Evaluation results
| Method | Links | |
|---|---|---|
| ADIW-KLTraining Time (s)=5.83, Imbalance ratio (ρ)=100, Fraction of minority classes (μ)=0.5, Backbone=LeNet-5, Optimizer=SGD2026.05 | 74.25 | |
| ADIW-KMTraining Time (s)=5.81, Imbalance ratio (ρ)=100, Fraction of minority classes (μ)=0.5, Backbone=LeNet-5, Optimizer=SGD2026.05 | 74.23 | |
| DIWTraining Time (s)=17.88, Imbalance ratio (ρ)=100, Fraction of minority classes (μ)=0.5, Backbone=LeNet-5, Optimizer=SGD2026.05 | 74.19 | |
| ADIW-LSTraining Time (s)=5.70, Imbalance ratio (ρ)=100, Fraction of minority classes (μ)=0.5, Backbone=LeNet-5, Optimizer=SGD2026.05 | 74.13 | |
| ADIW-WATraining Time (s)=7.79, Imbalance ratio (ρ)=100, Fraction of minority classes (μ)=0.5, Backbone=LeNet-5, Optimizer=SGD2026.05 | 73.14 | |
| Val-OnlyTraining Time (s)=0.02, Imbalance ratio (ρ)=100, Fraction of minority classes (μ)=0.5, Backbone=LeNet-5, Optimizer=SGD2026.05 | 65.55 |