Abstract
Most classification models treat all misclassifications equally. However, different classes may be related, and these hierarchical relationships must be considered in some classification problems. These problems can be addressed by using hierarchical information during training. Unfortunately, this information is not available for all datasets. Many classification-based metric learning methods use class representatives in embedding space to represent different classes. The relationships among the learned class representatives can then be used to estimate class hierarchical structures. If we have a predefined class hierarchy, the learned class representatives can be assessed to determine whether the metric learning model learned semantic distances that match our prior knowledge. In this work, we train a softmax classifier and three metric learning models with several training options on benchmark and real-world datasets. In addition to the standard classification accuracy, we evaluate the hierarchical inference performance by inspecting learned class representatives and the hierarchy-informed performance, i.e., the classification performance, and the metric learning performance by considering predefined hierarchical structures. Furthermore, we investigate how the considered measures are affected by various models and training options. When our proposed ProxyDR model is trained without using predefined hierarchical structures, the hierarchical inference performance is significantly better than that of the popular NormFace model. Additionally, our model enhances some hierarchy-informed performance measures under the same training options. We also found that convolutional neural networks (CNNs) with random weights correspond to the predefined hierarchies better than random chance.
Abstract (translated)
大多数分类模型都将所有误分类视为平等对待。然而,不同类别可能相互关联,在一些分类问题上,需要考虑这种层次关系。这些问题可以通过在训练期间使用层次信息来解决。不幸的是,这些信息并不适用于所有数据集。许多基于分类的度量学习方法使用嵌入空间中的类代表来代表不同类别。通过学习类代表之间的关系,可以估计类层次结构。如果我们有一个预先定义的类层次,则可以使用学习类代表来评估,以确定度量学习模型是否学习了与我们已有知识匹配的语义距离。在这项工作中,我们训练一个softmax分类器和三个度量学习模型,并在基准数据和实际数据集上使用多个训练选项。除了标准的分类准确性外,我们评估了层次推断性能,通过检查学习类代表和层次 informed 性能(即分类性能)以及考虑预先定义的类层次结构。此外,我们研究了各种模型和训练选项如何影响所考虑的措施。当我们的提议的代理DR模型在没有使用预先定义的类层次结构的情况下进行训练时,层次推断性能显著优于流行的范式Face模型。此外,我们的模型在相同的训练选项下增强了一些层次 informed 性能 measures。我们还发现,随机权重的卷积神经网络(CNNs)与预先定义的类层次更加匹配。
URL
https://arxiv.org/abs/2301.11065