arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.05142cs.CV
收藏

噪声度量学习中的平滑代理-锚丢失

Smooth Proxy-Anchor Loss for Noisy Metric Learning

Vilynx(Vilynx公司)

Carlos Roig, David Varas, Issey Masuda, Juan Carlos Riveiro, Elisenda Bou-Balust

摘要:

许多工业应用程序使用度量学习作为一种方法,以规避设计具有大量类的系统时的可扩展性问题。正因为如此,这一研究领域吸引了学术界和非学术界的极大兴趣。这些工业应用需要大规模的数据集,这些数据集通常是由Web数据生成的,因此通常包含大量的噪声标签。虽然度量学习系统对嘈杂的标签很敏感,但这通常不会在文献中得到解决,而是依赖于手动注释的数据集。在这项工作中,我们提出了一种度量学习方法,能够克服噪声标签的存在,使用我们的新的平滑代理锚损失。我们还提出了一个架构,使用上述损失与两个阶段的学习过程。首先,我们训练一个计算样本类置信度的置信度模块。其次,这些置信度用于加权每个样本对嵌入训练的影响。这导致能够提供鲁棒的样本嵌入的系统。我们将所描述的方法的性能与当前最先进的度量学习损失(基于代理和基于对)进行比较,当使用包含噪声标签的数据集进行训练时。结果显示,在MultiSimilarity和Proxy-Anchor Loss方面,Recall@1分别提高了2.63和3.29,证明了我们的方法在噪声标记条件下优于最先进的度量学习。

英文摘要:

Many industrial applications use Metric Learning as a way to circumvent scalability issues when designing systems with a high number of classes. Because of this, this field of research is attracting a lot of interest from the academic and non-academic communities. Such industrial applications require large-scale datasets, which are usually generated with web data and, as a result, often contain a high number of noisy labels. While Metric Learning systems are sensitive to noisy labels, this is usually not tackled in the literature, that relies on manually annotated datasets. In this work, we propose a Metric Learning method that is able to overcome the presence of noisy labels using our novel Smooth Proxy-Anchor Loss. We also present an architecture that uses the aforementioned loss with a two-phase learning procedure. First, we train a confidence module that computes sample class confidences. Second, these confidences are used to weight the influence of each sample for the training of the embeddings. This results in a system that is able to provide robust sample embeddings. We compare the performance of the described method with current state-of-the-art Metric Learning losses (proxy-based and pair-based), when trained with a dataset containing noisy labels. The results showcase an improvement of 2.63 and 3.29 in Recall@1 with respect to MultiSimilarity and Proxy-Anchor Loss respectively, proving that our method outperforms the state-of-the-art of Metric Learning in noisy labeling conditions.

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。

↑