提出混淆感知评分，分离难度评分与训练节奏影响。
Confusion-Aware Transfer Teacher Curriculum Learning Framework: Disentangling Scoring and Pacing Effects
- 设计双评估协议，独立验证难度评分与数据调度效果。
- 在20%数据下，混淆感知课程排序提升8.7%准确率。
- 适合关注数据效率与可解释性训练的开发者。
课程学习同时涉及样本难度评分和难样本引入节奏两个设计选择，难以区分其各自贡献。本文通过两种评估协议实现解耦：阶段测试子集用于独立验证评分函数，基准方案则对随机排序数据施加相同节奏。在迁移教师框架（TTF）中，提出一种混淆感知难度评分，综合考虑正确类别置信度及错误类别概率分布。在CIFAR-10上使用ResNet-18与VGG-16实验表明，该评分生成符合人类直觉、模型可解释的难度排序。然而，在全量数据下，无论正向或反向课程排序均未优于标准训练，说明仅改进评分无法克服TTF中课程学习的已知失效模式。相反，混淆感知课程排序在数据效率上表现稳定，20%数据下相较随机排序最高提升8.7个百分点，表明TTF具备成为高效数据训练方法的潜力。
原文摘要 · Abstract (English)
Curriculum learning couples two design choices, how samples are scored by difficulty and how harder samples are paced into training, making it difficult to attribute observed gains to either component. We disentangle these factors with two evaluation protocols: stage-wise test subsets that validate scoring functions independently of curriculum training, and a baseline that applies the same pacing schedule to randomly ordered data. Within the Transfer Teacher framework (TTF), we use these protocols to evaluate a confusion-aware difficulty score that considers both correct-class confidence and the probability distribution over incorrect classes. On CIFAR-10 with ResNet-18 and VGG-16, the proposed score produces model-interpretable difficulty rankings that align with human intuition. However, at full data, neither curriculum nor anti-curriculum ordering improves accuracy over standard training, indicating that improving the scoring function alone is insufficient to overcome the known failure modes of curriculum learning in TTF. In contrast, We find that confusion-aware curriculum ordering result in consistent data-efficiency benefits, outperforming random ordering by up to 8.7% points at the 20% data regime, suggesting the potential of TTF as a data-efficient training method.
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。