Abstract:

Real-world datasets often suffer from both noisy labels and long-tailed distributions, where rare classes are more prone to annotation errors. Existing methods typically ad- dress these issues separately or rely on unreliable noise pre-screening, leading to biased learning and unstable optimization. We propose Soft-label Refurbishment with Ensemble Learning (SoREL), a two-stage framework that jointly handles label noise and class imbalance. In the first stage, SoREL performs robust soft-label refurbishment via contrastive learning for unbiased representation learning and a Balanced Noise-tolerant Cross-entropy (BANC) loss for stable pre-screening. In the second stage, refurbished soft labels guide multi-expert ensemble learning, where experts specialize in many-, medium-, and few-shot classes. Soft- label-based class statistics further refine loss weighting to better match the true data distribution. Experiments on simulated and real-world noisy long-tailed datasets demonstrate that SoREL achieves 91.80%/67.59% on CIFAR-10/100-LT and 77.74% / 81.40% on Food-101N and Animal-10N, significantly outperforming prior methods.