Metraipolis › archive › dc_67df6946e15e

Evaluating Synthetic Skin Lesion Images for Classifier Training: A Safety-Aware Algorithm — arXiv:2611.02437

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02437
License (as archived)
CC0-1.0
Archived
2026-11-03T18:40:45.173Z
SHA-256 of the archived text
066c758f29986d670eaf86fc2f94735b484b00bad52f69f72f3e5be3376f1355
Stable URL of this page
https://metraipolis.com/documento/dc_67df6946e15e

How to cite

Evaluating Synthetic Skin Lesion Images for Classifier Training: A Safety-Aware Algorithm — arXiv:2611.02437 — arXiv (en), https://arxiv.org/abs/2611.02437 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_67df6946e15e (Metraipolis archive dc_67df6946e15e, sha256 066c758f29986d670eaf86fc2f94735b484b00bad52f69f72f3e5be3376f1355)
BibTeX
@misc{dc67df6946e15e,
  title = {Evaluating Synthetic Skin Lesion Images for Classifier Training: A Safety-Aware Algorithm — arXiv:2611.02437},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02437},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_67df6946e15e; sha256 066c758f29986d670eaf86fc2f94735b484b00bad52f69f72f3e5be3376f1355},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02437. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Skin cancer classifiers need large sets of annotated images, which are scarce, especially for rare lesion types. AI-generated images can fill the gap, but a generator produces images of widely varying quality, so selecting which images to retain is important. That choice usually rests on a single quality score, most often the Fréchet Inception Distance (FID), which has not been tested against what a classifier needs and cannot tell whether the generator memorizes its training photographs. We test that practice with a tournament of 16 quality metrics. Each metric alone selects a training subset from a pool of 275,472 images generated by a diffusion model (EDM2), and a classifier trained on each subset scores the metric per class. The tournament shows that no single metric serves every class: FID computed on Inception features gives the best classifier for one lesion type and no measurable advantage over random sampling for another, and the generation setting it prefers is also the one closest to the training images. We turn these per-class measurements into a safety-aware evaluation algorithm that weights each metric by its measured value in each class and removes images too close to a real training image. On the held-out ISIC-2018 test set, the algorithm improves Macro-$F_2$, a recall-weighted measure of classification performance, over the FID baseline for a Swin-B classifier by +0.0136 to +0.0164 across four safety thresholds (Bonferroni-corrected $p < 0.02$) and over random sampling by about +0.03, though not for ResNet-50. Tightening the threshold improves a memorization-safety score with no measurable change in utility, but every curated set remains less safe than random sampling. The results show a modest but statistically significant gain on the primary classifier, and offer a practical, safety-aware procedure for evaluating and using synthetic data.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.02437 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:12:54.770Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).