{"ID":2827823,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.15009","arxiv_id":"2512.15009","title":"Model Agnostic Preference Optimization for Medical Image Segmentation","abstract":"Preference optimization offers a scalable supervision paradigm based on relative preference signals, yet prior attempts in medical image segmentation remain model-specific and rely on low-diversity prediction sampling. In this paper, we propose MAPO (Model-Agnostic Preference Optimization), a training framework that utilizes Dropout-driven stochastic segmentation hypotheses to construct preference-consistent gradients without direct ground-truth supervision. MAPO is fully architecture- and dimensionality-agnostic, supporting 2D/3D CNN and Transformer-based segmentation pipelines. Comprehensive evaluations across diverse medical datasets reveal that MAPO consistently enhances boundary adherence, reduces overfitting, and yields more stable optimization dynamics compared to conventional supervised training.","short_abstract":"Preference optimization offers a scalable supervision paradigm based on relative preference signals, yet prior attempts in medical image segmentation remain model-specific and rely on low-diversity prediction sampling. In this paper, we propose MAPO (Model-Agnostic Preference Optimization), a training framework that ut...","url_abs":"https://arxiv.org/abs/2512.15009","url_pdf":"https://arxiv.org/pdf/2512.15009v1","authors":"[\"Yunseong Nam\",\"Jiwon Jang\",\"Dongkyu Won\",\"Sang Hyun Park\",\"Soopil Kim\"]","published":"2025-12-17T01:50:52Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\",\"Convolutional Neural Network\"]","has_code":false}