UNet [27] is widely used in semantic segmentation due to its simplicity and effectiveness. However, manually-designed architecture applied a large number of problem settings, either with no optimizations, or manual tuning, which time consuming can be sub-optimal. In this work, firstly, we propose Markov Random Field Neural Architecture Search (MRF-NAS) that extends improves the recent Adaptive ...

We present conditional random fields , a framework for building probabilistic models to segment and label sequence data. Conditional random fields offer several advantages over hidden Markov models and stochastic grammars for such tasks, including the ability to relax strong independence assumptions made in those models. Conditional random fields also avoid a fundamental limitation of maximum e...

In this paper we propose a fully connected energy function for Markov Random Field (MRF) modeling which is inspired by Spin-Glass Theory (SGT). Two major tasks in MRF modeling are how to define the neighborhood system for irregular sites and how to choose the energy function for a proper encoding of constraints. The proposed energy function offers two major advantages that makes it possible to ...

We present telescoping recursive representations for both continuous and discrete indexed noncausal Gauss-Markov random fields. Our recursions start at the boundary (for example, a hypersurface in R, d ≥ 1) and telescope inwards. Under appropriate conditions, the recursions for the random field are differential/difference representations driven by white noise, for which we can use standard recu...

Given a Gaussian Markov random field, we consider the problem of selecting a subset of variables to observe which minimizes the total expected squared prediction error of the unobserved variables. We first show that finding an exact solution is NP-hard even for a restricted class of Gaussian Markov random fields, called Gaussian free fields, which arise in semi-supervised learning and computer ...