Optimizing Class Distributions for Bias-Aware Multi-Class Learning
In multi-class image classification, class imbalance leads to degraded performance on safety-critical classes, biased and high-variance objective functions. To address this, we propose BiCDO—a data-centric, iterative class distribution optimization framework. Its core innovation is the first introduction of bias-aware Pareto-optimal distribution modeling, which dynamically adjusts per-class sample weights during training without modifying model architecture. BiCDO is agnostic to backbone networks (e.g., EfficientNet, ResNet, ConvNeXt) and applicable to any annotated multi-class dataset. Experiments on CIFAR-10 and iNaturalist21 demonstrate that BiCDO significantly improves overall accuracy and class-balanced performance—e.g., tail-class F1-score increases by up to 12.3%—while maintaining low computational overhead and straightforward deployment.