Proxy-based metric learning losses are superior to pair-based losses due to their fast convergence and low training complexity. However, existing proxy-based losses focus on learning class-discriminative features while overlooking the commonalities shared across classes which are potentially useful in describing and matching samples. Moreover, they ignore the implicit hierarchy of categories in real-world datasets, where similar subordinate classes can be grouped together. In this paper, we present a framework that leverages this implicit hierarchy by imposing a hierarchical structure on the proxies and can be used with any existing proxy-based loss. This allows our model to capture both class-discriminative features and class-shared characteristics without breaking the implicit data hierarchy. We evaluate our method on five established image retrieval datasets such as In-Shop and SOP. Results demonstrate that our hierarchical proxy-based loss framework improves the performance of existing proxy-based losses, especially on large datasets which exhibit strong hierarchical structure.
翻译:代用标准学习损失优于基于对等的损失,因为它们迅速趋同和低程度的培训复杂性。然而,现有的代用损失侧重于学习阶级差异性特征,而忽略了各阶层共有的、在描述和匹配样本方面可能有用的共同点。此外,它们忽视了真实世界数据集中隐含的类别等级,将类似的下属类别分组在一起。在本文件中,我们提出了一个框架,通过对代理人强加等级结构来利用这种隐含的等级,并可用于任何现有的代用损失。这使得我们的模型既能捕捉阶级差异性特征,又能捕捉阶级共享特征,同时又不打破隐含的数据等级。我们评估了我们关于In-Shop和SOP等五个既定图像检索数据集的方法。结果显示,我们基于等级的代用损失框架改善了现有代用损失的绩效,特别是具有强大等级结构的大型数据集的绩效。