A deep-structured fully-connected random field model for structured inference
This work addresses a computational bottleneck in combining two types of graphical models for researchers in machine learning, but it appears incremental as it builds on existing concepts without claiming major breakthroughs.
The study tackled the problem of unifying fully-connected and deep-structured graphical models for structured inference by introducing a deep-structured fully-connected random field (DFRF) model, which reduces computational complexity and is shown to be feasible for tasks like image segmentation.
There has been significant interest in the use of fully-connected graphical models and deep-structured graphical models for the purpose of structured inference. However, fully-connected and deep-structured graphical models have been largely explored independently, leaving the unification of these two concepts ripe for exploration. A fundamental challenge with unifying these two types of models is in dealing with computational complexity. In this study, we investigate the feasibility of unifying fully-connected and deep-structured models in a computationally tractable manner for the purpose of structured inference. To accomplish this, we introduce a deep-structured fully-connected random field (DFRF) model that integrates a series of intermediate sparse auto-encoding layers placed between state layers to significantly reduce computational complexity. The problem of image segmentation was used to illustrate the feasibility of using the DFRF for structured inference in a computationally tractable manner. Results in this study show that it is feasible to unify fully-connected and deep-structured models in a computationally tractable manner for solving structured inference problems such as image segmentation.