# Extending Music Annotation Schemas: Zero-Shot Prediction or Few-Shot Adaptation?

arXiv: https://arxiv.org/abs/2610.06920 · HTML: https://mlsanity.com/paper/2610.06920/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 21 of 21)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision](https://mlsanity.com/paper/2309.14181/) (2023)
- [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://mlsanity.com/paper/2306.00107/) (2023)
- [MuLan: A Joint Embedding of Music Audio and Natural Language](https://mlsanity.com/paper/2208.12415/) (2022)
- [Evaluation of CNN-based Automatic Music Tagging Models](https://mlsanity.com/paper/2006.00751/) (2020)
- [Contrastive Audio-Language Learning for Music](https://mlsanity.com/paper/2208.12208/) (2022)
- [CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages](https://mlsanity.com/paper/2502.10362/) (2025)
- [Music Flamingo: Scaling Music Understanding in Audio Language Models](https://mlsanity.com/paper/2511.10289/) (2025)
- [CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following](https://mlsanity.com/paper/2506.12285/) (2025)
- [Leveraging Hierarchical Structures for Few-Shot Musical Instrument Recognition](https://mlsanity.com/paper/2107.07029/) (2021)
- [Zero-shot Learning for Audio-based Music Classification and Tagging](https://mlsanity.com/paper/1907.02670/) (2019)
- [A data-driven approach to mid-level perceptual musical feature modeling](https://mlsanity.com/paper/1806.04903/) (2018)
- [LC-Protonets: Multi-Label Few-Shot Learning for World Music Audio Tagging](https://mlsanity.com/paper/2409.11264/) (2024)
- [Benchmarking Music Autotagging with MGPHot Expert Annotations vs. Generic Tag Datasets](https://mlsanity.com/paper/2509.06936/) (2025)
- [Towards Effective Negation Modeling in Joint Audio-Text Models for Music](https://mlsanity.com/paper/2601.13931/) (2026)

## Abstract (arXiv)

Automatic music annotation is typically tackled under the assumption of a fixed annotation schema. In practice, commercial music catalogs often need to accommodate new musical attributes as needs evolve. Given that expert music annotation is expensive, it is not evident which methodological approach is most effective at accommodating new attributes and backfilling existing tracks; audio-language models promise zero-shot prediction, but at what annotation budget does supervised adaptation become more compelling? We propose a benchmark based on the MGPHot popular music annotation dataset for simulating music schema extension across different annotation budgets. We investigate zero-shot prediction with audio-language models, learning new attributes from pretrained representations, and adapting models trained on existing annotations. Our results suggest that supervised adaptation is more effective than zero-shot prediction even with small annotation budgets, while frozen representation reuse remains the most effective approach for modest budgets without the tuning required by deeper adaptation.