Skip to content
arXiv cs.CV · Papers

A Unified Variational Framework for Deep Weakly Supervised Image Segmentation

arXiv:2607.19669v1 Announce Type: new Abstract: We propose a unified variational framework for image segmentation under sparse pixel-level supervision. Our method is based on a simplex-constrained Potts model with a smooth perimeter regularizer, yielding a convex, smooth energy functional that can be used as a training