The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving the robustness towards noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) remains under-explored. Existing noisy label learning methods designed for DML mainly discard suspicious noisy samples, resulting in a waste of the training data. To address this issue, we propose a noise-robust DML framework with SubGroup-based Positive-pair Selection (SGPS), which constructs reliable positive pairs for noisy samples to enhance the sample utilization. Specifically, SGPS first effectively identifies clean and noisy samples by a probability-based clean sample selectionstrategy. To further utilize the remaining noisy samples, we discover their potential similar samples based on the subgroup information given by a subgroup generation module and then aggregate them into informative positive prototypes for each noisy sample via a positive prototype generation module. Afterward, a new contrastive loss is tailored for the noisy samples with their selected positive pairs. SGPS can be easily integrated into the training process of existing pair-wise DML tasks, like image retrieval and face recognition. Extensive experiments on multiple synthetic and real-world large-scale label noise datasets demonstrate the effectiveness of our proposed method. Without any bells and whistles, our SGPS framework outperforms the state-of-the-art noisy label DML methods.

中文翻译：

---

通过基于子组的正对选择提高噪声稳健深度度量学习中的样本利用率


真实数据中存在嘈杂的标签会对深度学习模型的性能产生负面影响。尽管已经投入了大量研究工作来提高分类任务中对噪声标签的鲁棒性，但深度度量学习 （DML） 中的噪声标签问题仍未得到充分探索。现有的 DML 噪声标签学习方法主要丢弃可疑的噪声样本，导致训练数据的浪费。为了解决这个问题，我们提出了一个具有基于子组的正对选择 （SGPS） 的噪声鲁棒 DML 框架，该框架为噪声样品构建可靠的正对以提高样品利用率。具体来说，SGPS 首先通过基于概率的干净样本选择策略有效地识别干净和有噪声的样本。为了进一步利用剩余的噪声样本，我们根据子组生成模块给出的亚组信息发现它们的潜在相似样本，然后通过正原型生成模块将它们聚合为每个噪声样本的信息丰富的阳性原型。之后，为具有所选阳性对的噪声样本量身定制新的对比损失。SGPS 可以轻松集成到现有成对 DML 任务（如图像检索和人脸识别）的训练过程中。在多个合成和真实世界的大规模标签噪声数据集上进行的广泛实验证明了我们提出的方法的有效性。没有任何花里胡哨，我们的 SGPS 框架优于最先进的噪声标签 DML 方法。