Recently, the application of Contrastive Representation Learning (CRL) in learning with noisy labels (LNL) has shown promising advancements due to its remarkable ability to learn well-distributed representations for better distinguishing noisy labels. However, CRL is mainly used as a pre-training technique, leading to a complicated multi-stage training pipeline. We also observed that trivially combining CRL with supervised LNL methods decreases performance. Using different images from the same class as negative pairs in CRL creates optimization conflicts between CRL and the supervised loss. To address these two issues, we propose an end-to-end PLReMix framework that avoids the complicated pipeline by introducing a Pseudo-Label Relaxed (PLR) contrastive loss to alleviate the conflicts between losses. This PLR loss constructs a reliable negative set of each sample by filtering out its inappropriate negative pairs that overlap at the top k indices of prediction probabilities, leading to more compact semantic clusters than vanilla CRL. Furthermore, a two-dimensional Gaussian Mixture Model (GMM) is adopted to distinguish clean and noisy samples by leveraging semantic information and model outputs simultaneously, which is expanded on the previously widely used one-dimensional form. The PLR loss and a semi-supervised loss are simultaneously applied to train on the GMM divided clean and noisy samples. Experiments on multiple benchmark datasets demonstrate the effectiveness of the proposed method. Our proposed PLR loss is scalable, which can be easily integrated into other LNL methods and boost their performance. Codes will be available.

翻译：最近，对比表示学习（CRL）在噪声标签学习（LNL）中的应用因能学习良好分布的表示以更好区分噪声标签而展现出显著进展。然而，CRL主要作为预训练技术使用，导致复杂的多阶段训练流程。我们还观察到，将CRL与监督LNL方法简单结合会降低性能。在CRL中将同一类别的不同图像作为负对，会导致CRL与监督损失之间的优化冲突。为解决这两个问题，我们提出端到端PLReMix框架，通过引入伪标签松弛（PLR）对比损失缓解损失间的冲突，从而避免复杂流程。该PLR损失通过过滤预测概率前k个索引中重叠的不合适负对，为每个样本构建可靠负集，从而生成比原始CRL更紧凑的语义簇。此外，采用二维高斯混合模型（GMM）同时利用语义信息和模型输出来区分干净与噪声样本，这扩展了先前广泛使用的一维形式。PLR损失与半监督损失同时应用于GMM划分的干净和噪声样本训练。在多个基准数据集上的实验证明了所提方法的有效性。我们提出的PLR损失具有可扩展性，可轻松集成到其他LNL方法中并提升其性能。代码将公开。