Efficient Structured Prediction with Latent Variables for General Graphical Models
This work addresses the problem of efficient inference in complex structured prediction tasks with latent variables for computer vision researchers, representing an incremental improvement over existing methods.
The authors tackled structured prediction with latent variables for general graphical models by developing a unified framework with a local entropy approximation and efficient message passing algorithm, demonstrating superior performance to existing methods in image segmentation and 3D indoor scene understanding tasks.
In this paper we propose a unified framework for structured prediction with latent variables which includes hidden conditional random fields and latent structured support vector machines as special cases. We describe a local entropy approximation for this general formulation using duality, and derive an efficient message passing algorithm that is guaranteed to converge. We demonstrate its effectiveness in the tasks of image segmentation as well as 3D indoor scene understanding from single images, showing that our approach is superior to latent structured support vector machines and hidden conditional random fields.