ACD-U: 用机器遗忘进行不对称共教学以实现鲁棒学习的噪声标签
ACD-U: Asymmetric co-teaching with machine unlearning for robust learning with noisy labels
AI总结：
ACD-U通过不对称共教学和机器遗忘技术，有效纠正噪声标签带来的学习误差，提升模型在高噪声环境下的鲁棒性。
摘要：
深度神经网络在训练过程中容易记忆错误标签，这会降低其泛化能力。尽管最近的方法已经结合了样本选择与半监督学习（SSL）来利用记忆效应——即网络在干净数据上学习后再学习噪声数据——但它们无法在样本被错误分类后纠正选择错误。为了解决这个问题，我们提出了不对称共教学与不同架构（ACD）-U，一种使用不同模型架构并结合机器遗忘的不对称共教学框架。ACD-U通过两个核心机制解决这一限制。首先，其不对称共教学将对比语言图像预训练（CLIP）预训练的视觉Transformer与卷积神经网络（CNN）配对，利用它们互补的学习行为：预训练模型提供稳定的预测，而CNN则在训练过程中适应。这种不对称性，即视觉Transformer仅在干净样本上训练，而CNN通过SSL训练，有效缓解了确认偏见。其次，选择性遗忘通过损失轨迹分析和CLIP一致性检查来识别被错误记忆的样本，并通过基于Kullback-Leibler散度的遗忘去除其影响。这种方法将学习范式从被动的错误避免转变为主动的错误纠正。在合成和真实世界噪声数据集上，包括CIFAR-10/100、CIFAR-N、WebVision、Clothing1M和Red Mini-ImageNet的实验表明，该方法在高噪声环境和实例依赖噪声下表现出最先进的性能。代码可在https://github.com/meruemon/ACD-U上公开获取。
英文摘要：
Deep neural networks are prone to memorizing incorrect labels during training, which degrades their generalizability. Although recent methods have combined sample selection with semi-supervised learning (SSL) to exploit the memorization effect -- where networks learn from clean data before noisy data -- they cannot correct selection errors once a sample is misclassified. To overcome this, we propose asymmetric co-teaching with different architectures (ACD)-U, an asymmetric co-teaching framework that uses different model architectures and incorporates machine unlearning. ACD-U addresses this limitation through two core mechanisms. First, its asymmetric co-teaching pairs a contrastive language-image pretraining (CLIP)-pretrained vision Transformer with a convolutional neural network (CNN), leveraging their complementary learning behaviors: the pretrained model provides stable predictions, whereas the CNN adapts throughout training. This asymmetry, where the vision Transformer is trained only on clean samples and the CNN is trained through SSL, effectively mitigates confirmation bias. Second, selective unlearning enables post-hoc error correction by identifying incorrectly memorized samples through loss trajectory analysis and CLIP consistency checks, and then removing their influence via Kullback--Leibler divergence-based forgetting. This approach shifts the learning paradigm from passive error avoidance to active error correction. Experiments on synthetic and real-world noisy datasets, including CIFAR-10/100, CIFAR-N, WebVision, Clothing1M, and Red Mini-ImageNet, demonstrate state-of-the-art performance, particularly in high-noise regimes and under instance-dependent noise. The code is publicly available at https://github.com/meruemon/ACD-U.
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。
