# An Attention-based Approach to Hierarchical Multi-label Music Instrument Classification

arXiv: https://arxiv.org/abs/2302.08136 · HTML: https://mlsanity.com/paper/2302.08136/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2023.

## Built on by (most cited first, 7 of 7)

- [Deep Learning for Multi-Label Learning: A Comprehensive Survey](https://mlsanity.com/paper/2401.16549/) (2024)
- [OpenMU: Your Swiss Army Knife for Music Understanding](https://mlsanity.com/paper/2410.15573/) (2024)
- [Music Foundation Model as Generic Booster for Music Downstream Tasks](https://mlsanity.com/paper/2411.01135/) (2024)
- [Self-refining of Pseudo Labels for Music Source Separation with Noisy Labeled Data](https://mlsanity.com/paper/2307.12576/) (2023)
- [On the choice of the optimal temporal support for audio classification with Pre-trained embeddings](https://mlsanity.com/paper/2312.14005/) (2023)
- [Improving Multi-Label Contrastive Learning by Leveraging Label Distribution](https://mlsanity.com/paper/2501.19145/) (2025)
- [Zero-Shot Hierarchical Classification on the Common Procurement Vocabulary Taxonomy](https://mlsanity.com/paper/2405.09983/) (2024)

## Abstract (arXiv)

Although music is typically multi-label, many works have studied hierarchical music tagging with simplified settings such as single-label data. Moreover, there lacks a framework to describe various joint training methods under the multi-label setting. In order to discuss the above topics, we introduce hierarchical multi-label music instrument classification task. The task provides a realistic setting where multi-instrument real music data is assumed. Various hierarchical methods that jointly train a DNN are summarized and explored in the context of the fusion of deep learning and conventional techniques. For the effective joint training in the multi-label setting, we propose two methods to model the connection between fine- and coarse-level tags, where one uses rule-based grouped max-pooling, the other one uses the attention mechanism obtained in a data-driven manner. Our evaluation reveals that the proposed methods have advantages over the method without joint training. In addition, the decision procedure within the proposed methods can be interpreted by visualizing attention maps or referring to fixed rules.