Leveraging Hierarchical Structures for Few-Shot Musical Instrument Recognition
This work addresses the challenge of recognizing a wider set of musical instruments with limited data, which is incremental as it builds on existing few-shot learning methods.
The paper tackles the problem of few-shot musical instrument recognition by exploiting hierarchical relationships between instruments, resulting in a significant increase in classification accuracy and decrease in mistake severity for unseen instrument classes compared to a non-hierarchical baseline.
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.