用于对抗标签噪声的重组中位数损失
Regroup Median Loss for Combating Label Noise
AI总结：
针对小损失准则易误选类干净噪声样本的问题，提出RML重组均值与中位数损失并结合样本选择的半监督框架，显著提升噪声标签下的性能。
摘要：
深度模型训练过程需要大规模带标注数据的数据集。由于标注大量样本存在困难，由错误标注导致的标签噪声不可避免，从而造成模型性能低下和模型泛化能力较差。为对抗标签噪声，当前方法通常基于小损失准则选择干净样本，并使用这些样本进行训练。由于某些噪声样本与干净样本相似，这些基于小损失准则的方法仍会受到标签噪声影响。为解决该问题，本文提出重组中位数损失（Regroup Median Loss，RML），以降低选择噪声样本的概率并校正噪声样本的损失。RML基于一种新的损失处理方法，随机选择与训练样本具有相同标签的样本。随后，我们通过所提出的重组策略，将稳定的均值损失与鲁棒的中位数损失相结合，以获得针对噪声样本的鲁棒损失估计。为进一步提升模型对抗标签噪声的性能，我们提出一种新的样本选择策略，并基于RML构建了一种半监督方法。与最先进方法相比，对于传统训练模型和半监督模型，RML在合成数据集和复杂真实世界数据集上均取得显著提升。本文源代码已发布。
英文摘要：
The deep model training procedure requires large-scale datasets of annotated data. Due to the difficulty of annotating a large number of samples, label noise caused by incorrect annotations is inevitable, resulting in low model performance and poor model generalization. To combat label noise, current methods usually select clean samples based on the small-loss criterion and use these samples for training. Due to some noisy samples similar to clean ones, these small-loss criterion-based methods are still affected by label noise. To address this issue, in this work, we propose Regroup Median Loss (RML) to reduce the probability of selecting noisy samples and correct losses of noisy samples. RML randomly selects samples with the same label as the training samples based on a new loss processing method. Then, we combine the stable mean loss and the robust median loss through a proposed regrouping strategy to obtain robust loss estimation for noisy samples. To further improve the model performance against label noise, we propose a new sample selection strategy and build a semi-supervised method based on RML. Compared to state-of-the-art methods, for both the traditionally trained and semi-supervised models, RML achieves a significant improvement on synthetic and complex real-world datasets. The source code of the paper has been released.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
