A Probabilistic U-Net for Segmentation of Ambiguous Images
This addresses the challenge of handling inherent ambiguities in real-world vision applications, such as medical imaging, by providing multiple plausible segmentation hypotheses for clinical decision-making.
The paper tackles the problem of ambiguous image segmentation by proposing a generative model that learns a distribution over plausible segmentations, showing significant improvements over existing methods on lung abnormalities and Cityscapes tasks.
Many real-world vision problems suffer from inherent ambiguities. In clinical applications for example, it might not be clear from a CT scan alone which particular region is cancer tissue. Therefore a group of graders typically produces a set of diverse but plausible segmentations. We consider the task of learning a distribution over segmentations given an input. To this end we propose a generative segmentation model based on a combination of a U-Net with a conditional variational autoencoder that is capable of efficiently producing an unlimited number of plausible hypotheses. We show on a lung abnormalities segmentation task and on a Cityscapes segmentation task that our model reproduces the possible segmentation variants as well as the frequencies with which they occur, doing so significantly better than published approaches. These models could have a high impact in real-world applications, such as being used as clinical decision-making algorithms accounting for multiple plausible semantic segmentation hypotheses to provide possible diagnoses and recommend further actions to resolve the present ambiguities.