The Generalized A* Architecture

TL;DR

This paper introduces a generalized A* framework for efficiently computing lightest derivations in AI inference problems, utilizing hierarchies of abstractions to improve search in complex structures.

Contribution

It extends A* search to a broad class of derivation problems and proposes a hierarchical search algorithm for better inference in vision and language tasks.

Findings

Hierarchical search outperforms traditional methods in boundary estimation.

The new algorithm effectively integrates information across processing stages.

Applications demonstrate improvements in computer vision and NLP tasks.

Abstract

We consider the problem of computing a lightest derivation of a global structure using a set of weighted rules. A large variety of inference problems in AI can be formulated in this framework. We generalize A* search and heuristics derived from abstractions to a broad class of lightest derivation problems. We also describe a new algorithm that searches for lightest derivations using a hierarchy of abstractions. Our generalization of A* gives a new algorithm for searching AND/OR graphs in a bottom-up fashion. We discuss how the algorithms described here provide a general architecture for addressing the pipeline problem --- the problem of passing information back and forth between various stages of processing in a perceptual system. We consider examples in computer vision and natural language processing. We apply the hierarchical search algorithm to the problem of estimating the boundaries of convex objects in grayscale images and compare it to other search methods. A second set of experiments demonstrate the use of a new compositional model for finding salient curves in images.