# PBSCR: The Piano Bootleg Score Composer Recognition Dataset

arXiv: https://arxiv.org/abs/2401.16803 · HTML: https://mlsanity.com/paper/2401.16803/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 56 references that are in the map.
- First posted on arXiv 30 Jan 2024.

## 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)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs](https://mlsanity.com/paper/2101.02402/) (2021)
- [GiantMIDI-Piano: A large-scale MIDI dataset for classical piano music](https://mlsanity.com/paper/2010.07061/) (2020)
- [Byte Pair Encoding for Symbolic Music](https://mlsanity.com/paper/2301.11975/) (2023)
- [CLaMP: Contrastive Language-Music Pre-training for Cross-Modal Symbolic Music Information Retrieval](https://mlsanity.com/paper/2304.11029/) (2023)
- [Symbolic Music Representations for Classification Tasks: A Systematic Evaluation](https://mlsanity.com/paper/2309.02567/) (2023)
- [Concept-Based Techniques for "Musicologist-friendly" Explanations in a Deep Music Classifier](https://mlsanity.com/paper/2208.12485/) (2022)
- [Large-Scale MIDI-based Composer Classification](https://mlsanity.com/paper/2010.14805/) (2020)
- [Deep Composer Classification Using Symbolic Representation](https://mlsanity.com/paper/2010.00823/) (2020)
- [Composer Style Classification of Piano Sheet Music Images Using Language Model Pretraining](https://mlsanity.com/paper/2007.14587/) (2020)
- [MIDI Passage Retrieval Using Cell Phone Pictures of Sheet Music](https://mlsanity.com/paper/2004.10347/) (2020)
- [Convolutional Composer Classification](https://mlsanity.com/paper/1911.11737/) (2019)
- [Representations of Sound in Deep Learning of Audio Features from Music](https://mlsanity.com/paper/1712.02898/) (2017)
- [Using Cell Phone Pictures of Sheet Music To Retrieve MIDI Passages](https://mlsanity.com/paper/2004.11724/) (2020)
- [Optimizing Feature Extraction for Symbolic Music](https://mlsanity.com/paper/2307.05107/) (2023)
- [Camera-Based Piano Sheet Music Identification](https://mlsanity.com/paper/2007.14579/) (2020)

## Abstract (arXiv)

This article motivates, describes, and presents the PBSCR dataset for studying composer recognition of classical piano music. Our goal was to design a dataset that facilitates large-scale research on composer recognition that is suitable for modern architectures and training practices. To achieve this goal, we utilize the abundance of sheet music images and rich metadata on IMSLP, use a previously proposed feature representation called a bootleg score to encode the location of noteheads relative to staff lines, and present the data in an extremely simple format (2D binary images) to encourage rapid exploration and iteration. The dataset itself contains 40,000 62x64 bootleg score images for a 9-class recognition task, 100,000 62x64 bootleg score images for a 100-class recognition task, and 29,310 unlabeled variable-length bootleg score images for pretraining. The labeled data is presented in a form that mirrors MNIST images, in order to make it extremely easy to visualize, manipulate, and train models in an efficient manner. We include relevant information to connect each bootleg score image with its underlying raw sheet music image, and we scrape, organize, and compile metadata from IMSLP on all piano works to facilitate multimodal research and allow for convenient linking to other datasets. We release baseline results in a supervised and low-shot setting for future works to compare against, and we discuss open research questions that the PBSCR data is especially well suited to facilitate research on.