通过动态建模样本难度，实现高效抗标签噪声训练。
Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization
- 基于错误事件动态加权损失，实现细粒度样本优化。
- 在五个基准上超越现有方法，计算耗时降低75%。
- 无需调参，适合大规模噪声数据场景。
近期研究表明，深度神经网络在噪声标注下泛化性能下降。现有方法多聚焦于分离干净样本或修正标签，但存在计算开销大、超参数调优复杂、优化粒度粗等问题。为此，本文提出一种两阶段噪声学习框架，通过动态加权损失函数实现实例级优化，避免超参数调优。引入一种简单有效的新指标——错误事件（wrong event），动态建模每个样本的清洁度与难度，同时保持低计算成本。框架先收集错误事件信息并构建强基线模型，再基于概率模型对样本的错误事件信息进行鲁棒训练。在五个合成与真实世界标签噪声学习（LNL）基准上的实验表明，本方法在性能上超越当前最优，计算时间减少近75%，显著提升可扩展性。
原文摘要 · Abstract (English)
Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational costs, heavy hyperparameter tuning process, and coarse-grained optimization. To address these challenges, we propose a novel two-stage noisy learning framework that enables instance-level optimization through a dynamically weighted loss function, avoiding hyperparameter tuning. To obtain stable and accurate information about noise modeling, we introduce a simple yet effective metric, termed wrong event, which dynamically models the cleanliness and difficulty of individual samples while maintaining computational costs. Our framework first collects wrong event information and builds a strong base model. Then we perform noise-robust training on the base model, using a probabilistic model to handle the wrong event information of samples. Experiments on five synthetic and real-world LNL benchmarks demonstrate our method surpasses state-of-the-art methods in performance, achieves a nearly 75% reduction in computational time and improves model scalability.
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。