arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.11063cs.CV
收藏

增强样本利用:基于子组的正对选择的噪声鲁棒深度度量学习

Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection

University of Chinese Academy of Sciences(中国科学院大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)

Zhipeng Yu, Qianqian Xu, Yangbangyan Jiang, Yingfei Sun, Qingming Huang

AI总结:

针对深度度量学习中噪声标签导致样本浪费的问题,提出基于子组的正对选择(SGPS)框架,通过识别干净样本并为噪声样本构建可靠正对,增强样本利用,在多个数据集上超越现有方法。

摘要:

真实世界数据中噪声标签的存在对深度学习模型的性能产生负面影响。尽管大量研究工作致力于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。现有的针对DML设计的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。为解决这一问题,我们提出了一种基于子组的正对选择(SGPS)的噪声鲁棒DML框架,该框架为噪声样本构建可靠的正对以增强样本利用。具体而言,SGPS首先通过基于概率的干净样本选择策略有效识别干净和噪声样本。为进一步利用剩余的噪声样本,我们基于子组生成模块提供的子组信息发现其潜在相似样本,然后通过正原型生成模块为每个噪声样本聚合信息丰富的正原型。随后,针对噪声样本及其选定的正对定制新的对比损失。SGPS可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大规模标签噪声数据集上的大量实验证明了我们提出方法的有效性。无需任何花哨技巧,我们的SGPS框架优于最先进的噪声标签DML方法。代码可在https://github.com/smuelpeng/SGPS-NoiseFreeDML获取。

英文摘要:

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. Code is available at \url{https://github.com/smuelpeng/SGPS-NoiseFreeDML}.

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。

↑