论文标题
深度度量学习的内容丰富的样本感知代理
Informative Sample-Aware Proxy for Deep Metric Learning
论文作者
论文摘要
在各种有监督的深度度量学习方法中，代理方法取得了很高的检索精度。代理是嵌入式空间中的班级代表点，以与样本表示相似的方式基于替代样本相似性接收更新。在现有方法中，相对较少的样品可以产生较大的梯度幅度（即硬样品），并且相对较大的样品可以产生较小的梯度幅度（即，易于样品）。这些可以在更新中发挥重要作用。假设获得对这种极端样品的过多敏感性会使方法的普遍性恶化，我们提出了一种基于新型的基于代理的方法，称为“信息示例感知器”（Proxy-isa），直接使用计划的阈值功能更敏感地对每个样品进行了启发，从而直接修改每个样品的梯度权重因子，以使模型更敏感。与最先进的方法相比，在CUB-200-2011，CARS-196，Stanford Online产品和购物中心检索数据集的广泛实验证明了代理-ISA的优越性。
Among various supervised deep metric learning methods proxy-based approaches have achieved high retrieval accuracies. Proxies, which are class-representative points in an embedding space, receive updates based on proxy-sample similarities in a similar manner to sample representations. In existing methods, a relatively small number of samples can produce large gradient magnitudes (ie, hard samples), and a relatively large number of samples can produce small gradient magnitudes (ie, easy samples); these can play a major part in updates. Assuming that acquiring too much sensitivity to such extreme sets of samples would deteriorate the generalizability of a method, we propose a novel proxy-based method called Informative Sample-Aware Proxy (Proxy-ISA), which directly modifies a gradient weighting factor for each sample using a scheduled threshold function, so that the model is more sensitive to the informative samples. Extensive experiments on the CUB-200-2011, Cars-196, Stanford Online Products and In-shop Clothes Retrieval datasets demonstrate the superiority of Proxy-ISA compared with the state-of-the-art methods.
