Blending Learning and Inference in Structured Prediction

TL;DR

This paper introduces an efficient algorithm that combines learning and inference in structured prediction models, significantly speeding up training and enabling high-order graphical models for complex tasks.

Contribution

The paper presents a novel blending algorithm for learning and inference in structured predictors, improving efficiency and scalability over traditional methods.

Findings

Achieves state-of-the-art results in stereo estimation and semantic segmentation.

Demonstrates convergence to the optimal solution of primal and dual programs.

Enables learning of high-order graphical models with large parameter spaces.

Abstract

In this paper we derive an efficient algorithm to learn the parameters of structured predictors in general graphical models. This algorithm blends the learning and inference tasks, which results in a significant speedup over traditional approaches, such as conditional random fields and structured support vector machines. For this purpose we utilize the structures of the predictors to describe a low dimensional structured prediction task which encourages local consistencies within the different structures while learning the parameters of the model. Convexity of the learning task provides the means to enforce the consistencies between the different parts. The inference-learning blending algorithm that we propose is guaranteed to converge to the optimum of the low dimensional primal and dual programs. Unlike many of the existing approaches, the inference-learning blending allows us to learn efficiently high-order graphical models, over regions of any size, and very large number of parameters. We demonstrate the effectiveness of our approach, while presenting state-of-the-art results in stereo estimation, semantic segmentation, shape reconstruction, and indoor scene understanding.