Metraipolis › archive › dc_cbc7b8a8e887
Selective Prediction and Uncertainty-Aware Referral for Pap Smear Classification — arXiv:2609.17545
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.17545
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T16:16:08.821Z
- SHA-256 of the archived text
171781e8b8bee1c8d3aca84cf34cd7a7497cadf27bc2d8490728d8c7f8cfd6f5- Stable URL of this page
https://metraipolis.com/documento/dc_cbc7b8a8e887
How to cite
Selective Prediction and Uncertainty-Aware Referral for Pap Smear Classification — arXiv:2609.17545 — arXiv (en), https://arxiv.org/abs/2609.17545 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbc7b8a8e887 (Metraipolis archive dc_cbc7b8a8e887, sha256 171781e8b8bee1c8d3aca84cf34cd7a7497cadf27bc2d8490728d8c7f8cfd6f5)
BibTeX
@misc{dccbc7b8a8e887,
title = {Selective Prediction and Uncertainty-Aware Referral for Pap Smear Classification — arXiv:2609.17545},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.17545},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbc7b8a8e887; sha256 171781e8b8bee1c8d3aca84cf34cd7a7497cadf27bc2d8490728d8c7f8cfd6f5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17545. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deep learning models for cervical cytology are almost always evaluated as if every prediction must be acted upon, yet a screening system deployed alongside a cytopathologist need not classify every slide: it can defer the cases it is least certain about. Evaluating such a system requires asking not only how often it is correct, but whether its confidence ranks its errors to the bottom. This paper studies selective prediction and uncertainty-aware referral on the Herlev Pap smear dataset under a binary Normal-versus-Abnormal formulation. Two lightweight transformer backbones (Swin-Tiny, TinyViT-5M) are fine-tuned on Herlev from ImageNet-pretrained weights with weighted random sampling, calibrated by post-hoc temperature scaling fit on a held-out calibration subset, and compared against a soft-voting ensemble of both models. Discrimination is reported alongside expected calibration error (ECE) and, as the primary endpoint, the area under the risk-coverage curve (AURC). No statistically significant difference was detected between the two configurations in accuracy or macro-F1, yet the ensemble halves AURC (0.0022 vs. 0.0045, a 51.8% reduction, lower in all five folds) and extends the coverage at which zero errors are made from 18.3% to 72.8% of the pooled test predictions. The same ensemble is nonetheless worse calibrated in absolute terms (ECE 0.0339 vs. 0.0247) and produces more false negatives (14 vs. 10). These results separate two properties that are frequently conflated: the ability to rank predictions by trustworthiness, and the accuracy of the confidence values themselves. Ensembling improves the former while degrading the latter, and the former directly governs the observed risk-coverage tradeoff, whereas the latter governs the interpretation of the reported confidence values. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.17545 — 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 2026-10-15T15:45:19.712Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).