Music Instrument Classification Reprogrammed
This addresses data scarcity issues in Music Information Retrieval, offering a potentially generalizable solution for other tasks with similar constraints, though it is incremental as it builds on existing reprogramming methods.
The paper tackles the problem of limited annotated data in Music Instrument Classification by using reprogramming, a technique that adapts pre-trained neural networks from different tasks, achieving performance on par with or better than state-of-the-art systems while using fewer training parameters.
The performance of approaches to Music Instrument Classification, a popular task in Music Information Retrieval, is often impacted and limited by the lack of availability of annotated data for training. We propose to address this issue with "reprogramming," a technique that utilizes pre-trained deep and complex neural networks originally targeting a different task by modifying and mapping both the input and output of the pre-trained model. We demonstrate that reprogramming can effectively leverage the power of the representation learned for a different task and that the resulting reprogrammed system can perform on par or even outperform state-of-the-art systems at a fraction of training parameters. Our results, therefore, indicate that reprogramming is a promising technique potentially applicable to other tasks impeded by data scarcity.