Deterministic Mode Proposals: An Efficient Alternative to Generative Sampling for Ambiguous Segmentation

ArXi:2603.20191v1 Announce Type: new Many segmentation tasks, such as medical image segmentation or future state prediction, are inherently ambiguous, meaning that multiple predictions are equally correct. Current methods typically rely on generative models to capture this uncertainty. However, identifying the underlying modes of the distribution with these methods is computationally expensive, requiring large numbers of samples and post-hoc clustering. In this paper, we shift the focus from stochastic sampling to the direct generation of likely outcomes. We