论文标题
使用公制的原型学习利用类层次结构
Leveraging Class Hierarchies with Metric-Guided Prototype Learning
论文作者
论文摘要
在许多分类任务中，可以将目标类集组织为层次结构。该结构在类之间引起语义距离，并且可以以成本矩阵的形式汇总，该矩阵定义了类集合的有限度量。在本文中，我们建议通过将此指标集成到原型网络的监督中来对层次类结构进行建模。我们的方法依赖于共同学习特征提取网络和一组类原型，它们的相对排列在嵌入空间中遵循分层度量。我们表明，与传统方法和其他基于原型的策略相比，这种方法可以持续提高成本矩阵加权的错误率。此外，当诱导的指标包含对数据结构的见解时，我们的方法也提高了整体精度。从四个不同的公共数据集进行实验 - 从农业时间序列分类到深度图像语义分割 - 验证我们的方法。
In many classification tasks, the set of target classes can be organized into a hierarchy. This structure induces a semantic distance between classes, and can be summarised under the form of a cost matrix, which defines a finite metric on the class set. In this paper, we propose to model the hierarchical class structure by integrating this metric in the supervision of a prototypical network. Our method relies on jointly learning a feature-extracting network and a set of class prototypes whose relative arrangement in the embedding space follows an hierarchical metric. We show that this approach allows for a consistent improvement of the error rate weighted by the cost matrix when compared to traditional methods and other prototype-based strategies. Furthermore, when the induced metric contains insight on the data structure, our method improves the overall precision as well. Experiments on four different public datasets - from agricultural time series classification to depth image semantic segmentation - validate our approach.
