剔除训练早期误标但易预测的样本，提升噪声标签下的模型性能。
Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples
- 用后期模型状态重选早期自信样本，避免早期误判误导
- 在CIFAR、WebVision和ImageNet-1k上显著减少误标易例（MEEs）
- 适合处理含标签噪声的图像分类任务，尤其关注样本选择优化
样本选择是应对标签噪声的常用方法，旨在筛选出可信样本用于训练。尽管现有方法通过降低所选子集的噪声率取得良好效果，却常忽略所有误标样本对模型性能的影响并不相同。本文证明：训练初期即被模型正确预测的误标样本（称为误标易例，MEEs）对模型性能危害尤为严重。为此，我们提出早期剔除（Early Cutting）策略，引入再校准步骤，利用模型后期训练状态重新筛选早期识别的自信样本，从而避免早期学习带来的误导性置信度，有效过滤掉MEEs。在CIFAR、WebVision和全量ImageNet-1k数据集上的实验表明，该方法能有效提升样本选择质量与模型性能。
原文摘要 · Abstract (English)
Sample selection is a prevalent approach in learning with noisy labels, aiming to identify confident samples for training. Although existing sample selection methods have achieved decent results by reducing the noise rate of the selected subset, they often overlook that not all mislabeled examples harm the model's performance equally. In this paper, we demonstrate that mislabeled examples correctly predicted by the model early in the training process are particularly harmful to model performance. We refer to these examples as Mislabeled Easy Examples (MEEs). To address this, we propose Early Cutting, which introduces a recalibration step that employs the model's later training state to re-select the confident subset identified early in training, thereby avoiding misleading confidence from early learning and effectively filtering out MEEs. Experiments on the CIFAR, WebVision, and full ImageNet-1k datasets demonstrate that our method effectively improves sample selection and model performance by reducing MEEs.
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。