AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

MuSViT: A Foundation Vision Model for Sheet Music Representation

Carlos Penarrubia, Antonio Rios-Vila, Eliseo Fuentes-Martinez, Juan Martinez-Sevilla, Francisco Castellanos, María Alfaro-Contreras, Jorge Calvo-Zaragoza

ECCV 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use music-specific MAE pre-training (MuSViT) instead of the best general-purpose encoder, frozenMuSViT · Full-page score recognition (linear probing)SER (%): 48.6 -> 16.4Improved
fine-tune MuSViT instead of the prior state of the art on full-page recognitionMuSViT · Full-page score recognition (fine-tuning)SER (%): 20.0 -> 10.9Improved
music-specific pre-training for staff-level recognition under linear probing versus Qwen3-VLMuSViT · Staff-level score recognition (linear probing)SER (%): 21.0 -> 18.4Improved
fine-tune MuSViT versus task-specific state of the art on staff-level recognitionMuSViT · Staff-level score recognition (fine-tuning)SER (%): 8.0 -> 8.6No clear effect
use MuSViT instead of DINOv3-7B for frozen symbol detectionMuSViT · DeepScoresV2 (linear probing)mAP: 70.4 -> 79.7Improved
fine-tune MuSViT with LoRA and Faster R-CNN versus Transformer-based state of the artMuSViT · DeepScoresV2 (fine-tuning)mAP50: 90.5 -> 97.0Improved
use MuSViT instead of prior state of the art for difficulty classification (fine-tuning)MuSViT · Score difficulty classification (fine-tuning)Acc0 (%): 38.4 -> 54.2Improved
use full MuSViT instead of MuSViT-Light for fine-tuned difficulty classificationMuSViT · Score difficulty classification (fine-tuning)Acc0 (%): 54.0 -> 54.2No clear effect
add synthetic warm-up stage (two-stage curriculum) before IMSLP MAE training (ablation)MuSViT pre-training · Pre-training stability (effective rank)embedding effective rankImproved
use MuSViT embeddings instead of general-purpose encoders for embedding-transcription alignmentMuSViT · Mozarteum and Polish Digital ScoresSpearman correlation (histogram): -0.009 -> 0.714Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy