用置信度评估优化不平衡噪声数据的训练，提升模型鲁棒性。
Conformal-in-the-Loop for Learning with Imbalanced Noisy Data
- 基于置信区间动态调整样本权重并剔除不可靠样本
- 在噪声与不平衡数据下，准确率最高提升6.1%，分割mIoU提升5.0
- 适合真实场景中标签不均衡且含噪声的数据集
类别不平衡与标签噪声广泛存在于大规模数据集中，但多数机器学习研究假设数据为均匀且标注正确，这与现实情况不符。现有方法通常单独处理标签噪声或类别不平衡，当两者共存时表现不佳。本文提出一种基于置信预测的训练框架Conformal-in-the-Loop（CitL），通过评估样本不确定性来调整权重并剔除不可靠样本，增强模型在低计算成本下的鲁棒性与准确性。大量实验表明，CitL能有效聚焦于对模型影响大的数据，在噪声与不平衡数据上持续提升性能，分类准确率最高提升6.1%，分割任务中mIoU提升5.0。代码已公开：CitL。
原文摘要 · Abstract (English)
Class imbalance and label noise are pervasive in large-scale datasets, yet much of machine learning research assumes well-labeled, balanced data, which rarely reflects real world conditions. Existing approaches typically address either label noise or class imbalance in isolation, leading to suboptimal results when both issues coexist. In this work, we propose Conformal-in-the-Loop (CitL), a novel training framework that addresses both challenges with a conformal prediction-based approach. CitL evaluates sample uncertainty to adjust weights and prune unreliable examples, enhancing model resilience and accuracy with minimal computational cost. Our extensive experiments include a detailed analysis showing how CitL effectively emphasizes impactful data in noisy, imbalanced datasets. Our results show that CitL consistently boosts model performance, achieving up to a 6.1% increase in classification accuracy and a 5.0 mIoU improvement in segmentation. Our code is publicly available: CitL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。