通过信息发散重加权，让模型自动遗忘噪声标签样本。
Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels
- 基于信息发散邻域的优化目标，自适应降低噪声样本影响。
- 在对称、非对称、人工标注及真实场景噪声下均优于现有方法。
- 计算开销接近标准交叉熵，适合实际部署场景。
我们提出ANTIDOTE，一种面向噪声标签学习的新损失函数，其定义基于信息发散邻域的松弛。利用凸对偶性，我们将其重构成一种对抗训练形式，计算成本与标准交叉熵损失相近。该方法在学习过程中自适应地减弱噪声标签样本的影响，表现出类似遗忘的行为。ANTIDOTE在标签噪声固有的训练数据或标签可被篡改的实际环境中均表现有效。在对称、非对称、人工标注及真实世界标签噪声等多种场景下的广泛实验表明，ANTIDOTE在性能上超越当前主流损失函数，且时间复杂度接近标准交叉熵损失。
原文摘要 · Abstract (English)
We introduce ANTIDOTE, a new class of objectives for learning under noisy labels which are defined in terms of a relaxation over an information-divergence neighborhood. Using convex duality, we provide a reformulation as an adversarial training method that has similar computational cost to training with standard cross-entropy loss. We show that our approach adaptively reduces the influence of the samples with noisy labels during learning, exhibiting a behavior that is analogous to forgetting those samples. ANTIDOTE is effective in practical environments where label noise is inherent in the training data or where an adversary can alter the training labels. Extensive empirical evaluations on different levels of symmetric, asymmetric, human annotation, and real-world label noise show that ANTIDOTE outperforms leading comparable losses in the field and enjoys a time complexity that is very close to that of the standard cross entropy loss.
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。