From UNI2-h to ConvNeXt-T: Lightweight Nuclei Instance Segmentation via Knowledge Distillation
On the map: Knowledge distillation → Distillation for medical imaging
Abstract (arXiv)
Nuclei instance segmentation is a core task in digital pathology, yet high-accuracy models rely on large vision transformer (ViT) encoders whose inference speed cannot meet real-time clinical demands. We propose a lightweight scheme that distills the UNI2-h pathology foundation model into a ConvNeXt-Tiny student (Ours-T, 34.7M parameters, 1/20 of the teacher) via output-level knowledge distillation. Ours-T achieves an mPQ of 0.519 on PanNuke (98.8% of the teacher), a zero-shot bPQ of 0.668 on MoNuSeg, and an inference speed of 634.3 img/s, requiring only 0.045 s for full-resolution 1024^2 analysis (21.8x speedup). Experiments further show that multi-scale gated convolution (MALA) yields no gain under ViT encoders, and output-level distillation alone suffices for efficient knowledge transfer.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Distillation for medical imaging, one of 12 directions in Knowledge distillation. Builds on 7 of its 13 references that are in the map. First posted on arXiv 28 Sep 2026.
Builds on
7 of 13 references.
References · 7
- 2015Distilling the Knowledge in a Neural Networkcited by 10,324
- 2023Segment Anythingcited by 8,234
- 2017Mask R-CNNcited by 7,277
- 2022A ConvNet for the 2020scited by 3,579
- 2018CBAM: Convolutional Block Attention Modulecited by 2,477
- 2018HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Imagescited by 388
- 2023CellViT: Vision Transformers for Precise Cell Segmentation and Classificationcited by 108
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023HoVer-UNet: Accelerating HoVerNet with UNet-based multi-class nuclei segmentation via knowledge distillation
- 2026Computationally Efficient Pathology Segmentation using Knowledge Distillation from Foundation Models
- 2025MUSE: Multi-Scale Dense Self-Distillation for Nucleus Detection and Classification
- 2021Efficient Medical Image Segmentation Based on Knowledge Distillation
- 2023Diffusion-based Data Augmentation for Nuclei Image Segmentation
- 2024Enhancing Weakly-Supervised Histopathology Image Segmentation with Knowledge Distillation on MIL-Based Pseudo-Labels
- 2023NASDM: Nuclei-Aware Semantic Histopathology Image Generation Using Diffusion Models
- 2023TransNuSeg: A Lightweight Multi-Task Transformer for Nuclei Segmentation