An MRF-UNet Product of Experts for Image Segmentation

Understand

While convolutional neural networks (CNNs) trained by back-propagation have seen unprecedented success at semantic segmentation tasks, they are known to struggle on out-of-distribution data.

• Markov random fields (MRFs) on the other hand, encode simpler distributions over labels that, although less flexible than UNets, are less prone to over-fitting.
• In this paper, we propose to fuse both strategies by computing the product of distributions of a UNet and an MRF.
• As this product is intractable, we solve for an approximate distribution using an iterative mean-field approach.