Deep learning work on musical instrument recognition has generally focused on instrument classes for which we have abundant data. In this work, we exploit hierarchical relationships between instruments in a few-shot learning setup to enable classification of a wider set of musical instruments, given a few examples at inference. We apply a hierarchical loss function to the training of prototypical networks, combined with a method to aggregate prototypes hierarchically, mirroring the structure of a predefined musical instrument hierarchy. These extensions require no changes to the network architecture and new levels can be easily added or removed. Compared to a non-hierarchical few-shot baseline, our method leads to a significant increase in classification accuracy and significant decrease mistake severity on instrument classes unseen in training.

翻译：关于乐器识别的深层学习工作一般侧重于我们拥有丰富数据的仪器类。在这项工作中,我们利用一些短短学习装置中仪器之间的等级关系,以便能够对一系列更广泛的乐器进行分类,我们举出了几个推理的例子。我们把等级损失功能应用于对原型网络的培训,同时采用一种按等级分类的原型集成的方法,反映预先界定的乐器级结构的结构。这些扩展不需要改变网络结构,新的等级可以很容易地被添加或删除。与非等级的微小基准相比,我们的方法导致分类准确性大幅提高,在培训中看不见的仪器类中的误差严重性显著降低。