{"ID":2839547,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.15406","arxiv_id":"2511.15406","title":"Controlling False Positives in Image Segmentation via Conformal Prediction","abstract":"Reliable semantic segmentation is essential for clinical decision making, yet deep models rarely provide explicit statistical guarantees on their errors. We introduce a simple post-hoc framework that constructs confidence masks with distribution-free, image-level control of false-positive predictions. Given any pretrained segmentation model, we define a nested family of shrunken masks obtained either by increasing the score threshold or by applying morphological erosion. A labeled calibration set is used to select a single shrink parameter via conformal prediction, ensuring that, for new images that are exchangeable with the calibration data, the proportion of false positives retained in the confidence mask stays below a user-specified tolerance with high probability. The method is model-agnostic, requires no retraining, and provides finite-sample guarantees regardless of the underlying predictor. Experiments on a polyp-segmentation benchmark demonstrate target-level empirical validity. Our framework enables practical, risk-aware segmentation in settings where over-segmentation can have clinical consequences. Code at https://github.com/deel-ai-papers/conseco.","short_abstract":"Reliable semantic segmentation is essential for clinical decision making, yet deep models rarely provide explicit statistical guarantees on their errors. We introduce a simple post-hoc framework that constructs confidence masks with distribution-free, image-level control of false-positive predictions. Given any pretrai...","url_abs":"https://arxiv.org/abs/2511.15406","url_pdf":"https://arxiv.org/pdf/2511.15406v1","authors":"[\"Luca Mossina\",\"Corentin Friedrich\"]","published":"2025-11-19T13:02:50Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":606881,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839547,"paper_url":"https://arxiv.org/abs/2511.15406","paper_title":"Controlling False Positives in Image Segmentation via Conformal Prediction","repo_url":"https://github.com/deel-ai-papers/conseco","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}