Pith Number

pith:YUXUQNFI

pith:2026:YUXUQNFI4ZTTPXM22QT35OF4DP

not attested not anchored not stored refs resolved

Flow Matching with Optimized Subclass Priors for Medical Image Augmentation

Bernhard Kainz, Felix N\"utzel, Mischa Dombrowski

Partitioning coarse labels into latent submodes and learning subclass-conditioned sources lets flow matching generate more faithful rare medical images while improving downstream classifier accuracy.

arxiv:2605.16469 v1 · 2026-05-15 · eess.IV · cs.CV

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{YUXUQNFI4ZTTPXM22QT35OF4DP}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

On long-tailed chest X-ray (MIMIC-LT, NIH-LT) and CT slice (CT-RATE) benchmarks the proposed method consistently improves tail-class generation fidelity and diversity (FID, IRS) and is a promising augmentation strategy that reliably improves downstream balanced accuracy and macro-F1 over a non-augmented baseline across modalities.

C2weakest assumption

That partitioning coarse labels into coherent submodes via Gaussian mixture modeling in the generative model's latent space will yield useful subclasses, and that learning subclass-conditioned source distributions will shorten transport paths and reduce dispersion without introducing new biases or degeneracies that the geometric control cannot fully mitigate.

C3one line summary

Optimizes subclass priors in flow matching via latent GMM partitioning and conditioned sources to improve rare disease image generation fidelity, diversity, and downstream classification on long-tailed medical datasets.

References

35 extracted · 35 resolved · 0 Pith anchors

[1] Adaloglou, N., Kaiser, T., Michels, F., Kollmann, M.: Rethinking cluster- conditioned diffusion models for label-free image synthesis. In: WACV’25. pp. 3603–3613. IEEE (2025) 2025

[2] Bao, F., Li, C., Sun, J., Zhu, J.: Why are conditional generative models better than unconditional ones? In: NeurIPS’22 Workshop on Score-Based Methods (2022) 2022

[3] Boecking, B., Usuyama, N., Bannur, S., Castro, D.C., Schwaighofer, A., Hyland, S., Wetscherek, M., Naumann, T., Nori, A., Alvarez-Valle, J., Poon, H., Oktay, O.: Making the most of text semantics to i 2022

[4] In: MICCAI’25 2025

[5] In: BRIDGE/DeCaF @ MICCAI’25 2026

Receipt and verification

First computed	2026-05-20T00:02:23.576283Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c52f4834a8e66737dd9ad427beb8bc1bc18be41456ede053a42489a67d31d9bc

Aliases

arxiv: 2605.16469 · arxiv_version: 2605.16469v1 · doi: 10.48550/arxiv.2605.16469 · pith_short_12: YUXUQNFI4ZTT · pith_short_16: YUXUQNFI4ZTTPXM2 · pith_short_8: YUXUQNFI

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/YUXUQNFI4ZTTPXM22QT35OF4DP \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: c52f4834a8e66737dd9ad427beb8bc1bc18be41456ede053a42489a67d31d9bc

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e0bc428d4b8850def47bccafc0112c2e2ee01e4bce4141ed6ff20cd2fba5d370",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "eess.IV",
    "submitted_at": "2026-05-15T12:05:15Z",
    "title_canon_sha256": "8d52f725c9dc02e657ac6bcbc0f31d46273c841520ac15935d6c94234808dfad"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16469",
    "kind": "arxiv",
    "version": 1
  }
}