# MuSViT: A Foundation Vision Model for Sheet Music Representation

arXiv: https://arxiv.org/abs/2606.31811 · HTML: https://mlsanity.com/paper/2606.31811/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 30 Jun 2026.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Understanding Dimensional Collapse in Contrastive Self-supervised Learning](https://mlsanity.com/paper/2110.09348/) (2021)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities](https://mlsanity.com/paper/2402.01831/) (2024)
- [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://mlsanity.com/paper/2306.00107/) (2023)
- [KOSMOS-2.5: A Multimodal Literate Model](https://mlsanity.com/paper/2309.11419/) (2023)
- [MuLan: A Joint Embedding of Music Audio and Natural Language](https://mlsanity.com/paper/2208.12415/) (2022)
- [How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders](https://mlsanity.com/paper/2210.08344/) (2022)
- [Understanding Optical Music Recognition](https://mlsanity.com/paper/1908.03608/) (2019)
- [Masked Image Modeling: A Survey](https://mlsanity.com/paper/2408.06687/) (2024)
- [End-to-End Full-Page Optical Music Recognition for Pianoform Sheet Music](https://mlsanity.com/paper/2405.12105/) (2024)
- [Predicting performance difficulty from piano sheet music images](https://mlsanity.com/paper/2309.16287/) (2023)
- [Towards Explainable and Interpretable Musical Difficulty Estimation: A Parameter-efficient Approach](https://mlsanity.com/paper/2408.00473/) (2024)

## Abstract (arXiv)

Foundation models have transformed vision and language processing by providing rich, reusable representations that transfer across diverse tasks. Sheet music, as a visual encoding of musical language, lacks such a strong domain-specific backbone. We introduce MuSViT (Music Score Vision Transformer): the first foundation vision model for sheet music representation -- a ViT encoder pre-trained via Masked Autoencoders on 9.7 million pages from the IMSLP. To handle the complexity of real-world scores, we adopt a two-stage curriculum: a synthetic warm-up on typeset scores followed by large-scale training on the full IMSLP corpus. We evaluate MuSViT on four downstream tasks -- full-page and staff-level music score recognition, music symbol detection, and score difficulty classification -- under two scenarios: linear probing (frozen encoder) and fine-tuning. Under linear probing, MuSViT consistently outperforms modern vision encoders, revealing that general-purpose representations, regardless of scale, fall systematically short on the structured symbolic properties of musical notation. Under fine-tuning, MuSViT generally improves upon task-specific state-of-the-art methods. An additional embedding-transcription consistency analysis reveals that MuSViT encodes symbolic musical structure directly in its representation space -- unlike other encoders, whose embeddings do not correlate with music notation content. These results establish MuSViT as a foundation backbone for sheet music understanding.