{"ID":2863694,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24913","arxiv_id":"2509.24913","title":"Segmentor-Guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesis","abstract":"Counterfactual image generation is a powerful tool for augmenting training data, de-biasing datasets, and modeling disease. Current approaches rely on external classifiers or regressors to increase the effectiveness of subject-level interventions (e.g., changing the patient's age). For structure-specific interventions (e.g., changing the area of the left lung in a chest radiograph), we show that this is insufficient, and can result in undesirable global effects across the image domain. Previous work used pixel-level label maps as guidance, requiring a user to provide hypothetical segmentations which are tedious and difficult to obtain. We propose Segmentor-guided Counterfactual Fine-Tuning (Seg-CFT), which preserves the simplicity of intervening on scalar-valued, structure-specific variables while producing locally coherent and effective counterfactuals. We demonstrate the capability of generating realistic chest radiographs, and we show promising results for modeling coronary artery disease. Code: https://github.com/biomedia-mira/seg-cft.","short_abstract":"Counterfactual image generation is a powerful tool for augmenting training data, de-biasing datasets, and modeling disease. Current approaches rely on external classifiers or regressors to increase the effectiveness of subject-level interventions (e.g., changing the patient's age). For structure-specific interventions...","url_abs":"https://arxiv.org/abs/2509.24913","url_pdf":"https://arxiv.org/pdf/2509.24913v2","authors":"[\"Tian Xia\",\"Matthew Sinclair\",\"Andreas Schuh\",\"Fabio De Sousa Ribeiro\",\"Raghav Mehta\",\"Rajat Rasal\",\"Esther Puyol-Antón\",\"Samuel Gerber\",\"Kersten Petersen\",\"Michiel Schaap\",\"Ben Glocker\"]","published":"2025-09-29T15:19:09Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":609043,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2863694,"paper_url":"https://arxiv.org/abs/2509.24913","paper_title":"Segmentor-Guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesis","repo_url":"https://github.com/biomedia-mira/seg-cft","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}