Skip to content
AI News HubLIVE
Original source2 min read

Exemplar: Classical Priors Complement Frozen Features for Few-Shot Microscopy Segmentation at Native Resolution

Summary

Exemplar is a few-shot biomedical segmenter that fuses a frozen DINOv3 backbone with a fixed bank of classical native-resolution filter responses in one lightweight head fitted from support masks alone. On an eleven-dataset panel it reaches 0.782, beating either branch alone, and leads 54 of 55 method-dataset comparisons. With a single annotated mask it scores 0.703 versus 0.682 for a from-scratch nnU-Net trained on the same mask.

SourcearXiv Computer VisionAuthor: Michal Pr\r{u}\v{s}ek, Adam Novoz\'amsk\'y, Filip \v{S}roubek
Exemplar: Classical Priors Complement Frozen Features for Few-Shot Microscopy Segmentation at Native Resolution
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 2 Sep 2026]

Title:Exemplar: Classical Priors Complement Frozen Features for Few-Shot Microscopy Segmentation at Native Resolution

View a PDF of the paper titled Exemplar: Classical Priors Complement Frozen Features for Few-Shot Microscopy Segmentation at Native Resolution, by Michal Pr\r{u}\v{s}ek and 2 other authors

View PDF HTML (experimental)

Abstract:Segmenting a new biomedical dataset usually means a domain-specific model trained on substantial annotation, or a foundation model steered at inference time. We present Exemplar, a few-shot segmenter that fuses a frozen DINOv3 backbone with a fixed bank of classical native-resolution filter responses in one lightweight head, fitted from the support masks alone. In the few-mask, native-resolution regime, classical priors and frozen self-supervised features are complementary: fused in one head, a single fixed configuration spans eleven biomedical imaging datasets. Under the same head, the classical bank alone reaches 0.693 on the eleven-dataset panel, scored by foreground intersection-over-union or centreline Dice, and the frozen features alone 0.672; the bank leads on seven of the eleven and the features on the rest, and fused they reach 0.782. Against five forward-pass few-shot methods, Exemplar leads in 54 of 55 method-dataset comparisons, 52 of them significant after Holm correction. From a single annotated mask it reaches 0.703 on the same panel, against 0.682 for a from-scratch nnU-Net trained on that same mask. At eight masks nnU-Net overtakes it on the panel mean, chiefly on centreline agreement, but takes 16-77x longer to fit.

Comments: 5 pages, 3 figures, 2 tables. Code, configurations, and the per-image score records behind every reported number: this https URL

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

ACM classes: I.4.6; I.2.10; J.3

Cite as: arXiv:2609.03080 [cs.CV]

(or arXiv:2609.03080v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2609.03080

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Michal Prusek [view email] [v1] Wed, 2 Sep 2026 18:49:58 UTC (3,358 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Exemplar: Classical Priors Complement Frozen Features for Few-Shot Microscopy Segmentation at Native Resolution, by Michal Pr\r{u}\v{s}ek and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Fuses frozen DINOv3 features with a fixed bank of classical filter responses in a single lightweight head fitted only from few-shot support masks.
  • On eleven biomedical datasets, the classical bank alone scores 0.693, frozen features alone 0.672, and the fused head 0.782 with one fixed configuration.
  • Leads five forward-pass few-shot methods in 54 of 55 method-dataset comparisons, 52 significant after Holm correction.
  • At one mask, 0.703 beats a from-scratch nnU-Net at 0.682; at eight masks nnU-Net overtakes on panel mean but takes 16-77x longer to fit.

Highlights and analysis are generated automatically and may contain errors. Check the original source.