# MUSE: Multi-Scale Dense Self-Distillation for Nucleus Detection and Classification

arXiv: https://arxiv.org/abs/2511.05170 · HTML: https://mlsanity.com/paper/2511.05170/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Distillation for medical imaging, one of 12 directions in Knowledge distillation.
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 7 Nov 2025.

## Placed in

- Knowledge distillation / [Distillation for medical imaging](https://mlsanity.com/distill/distillation-for-medical-imaging/)

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [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)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Self-Supervised Learning of Pretext-Invariant Representations](https://mlsanity.com/paper/1912.01991/) (2019)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images](https://mlsanity.com/paper/1812.06499/) (2018)
- [Benchmarking Self-Supervised Learning on Diverse Pathology Datasets](https://mlsanity.com/paper/2212.04690/) (2022)
- [CellViT: Vision Transformers for Precise Cell Segmentation and Classification](https://mlsanity.com/paper/2306.15350/) (2023)
- [OCELOT: Overlapped Cell on Tissue Dataset for Histopathology](https://mlsanity.com/paper/2303.13110/) (2023)
- [CellViT++: Energy-Efficient and Adaptive Cell Segmentation and Classification Using Foundation Models](https://mlsanity.com/paper/2501.05269/) (2025)
- [Structure Embedded Nucleus Classification for Histopathology Images](https://mlsanity.com/paper/2302.11416/) (2023)
- [Cell Graph Transformer for Nuclei Classification](https://mlsanity.com/paper/2402.12946/) (2024)
- [DPA-P2PNet: Deformable Proposal-aware P2PNet for Accurate Point-based Cell Detection](https://mlsanity.com/paper/2303.02602/) (2023)

## Built on by (most cited first, 2 of 2)

- [NuNext: Reframing Nucleus Detection as Next-Point Detection](https://mlsanity.com/paper/2603.07098/) (2026)
- [DeNuC: Decoupling Nuclei Detection and Classification in Histopathology](https://mlsanity.com/paper/2603.04240/) (2026)

## Abstract (arXiv)

Nucleus detection and classification (NDC) in histopathology analysis is a fundamental task that underpins a wide range of high-level pathology applications. However, existing methods heavily rely on labor-intensive nucleus-level annotations and struggle to fully exploit large-scale unlabeled data for learning discriminative nucleus representations. In this work, we propose MUSE (MUlti-scale denSE self-distillation), a novel self-supervised learning method tailored for NDC. At its core is NuLo (Nucleus-based Local self-distillation), a coordinate-guided mechanism that enables flexible local self-distillation based on predicted nucleus positions. By removing the need for strict spatial alignment between augmented views, NuLo allows critical cross-scale alignment, thus unlocking the capacity of models for fine-grained nucleus-level representation. To support MUSE, we design a simple yet effective encoder-decoder architecture and a large field-of-view semi-supervised fine-tuning strategy that together maximize the value of unlabeled pathology images. Extensive experiments on three widely used benchmarks demonstrate that MUSE effectively addresses the core challenges of histopathological NDC. The resulting models not only surpass state-of-the-art supervised baselines but also outperform generic pathology foundation models.