Reasoning and Algorithm Selection Augmented Symbolic Segmentation

TL;DR

This paper proposes an algorithm selection approach for symbolic segmentation, improving accuracy by 2% through combining multiple algorithms based on input features and image attributes.

Contribution

It introduces a novel method framing symbolic segmentation as an algorithm selection problem, enhancing segmentation accuracy by integrating multiple algorithms.

Findings

Algorithm selection improves segmentation accuracy by 2%.

Combining multiple segmentation results yields better outcomes.

State-of-the-art algorithms benefit from the proposed selection mechanism.

Abstract

In this paper we present an alternative method to symbolic segmentation: we approach symbolic segmentation as an algorithm selection problem. That is, let there be a set A of available algorithms for symbolic segmentation, a set of input features $F$, a set of image attribute $\mathbb{A}$ and a selection mechanism $S(F,\mathbb{A},A)$ that selects on a case by case basis the best algorithm. The semantic segmentation is then an optimization process that combines best component segments from multiple results into a single optimal result. The experiments compare three different algorithm selection mechanisms using three selected semantic segmentation algorithms. The results show that using the current state of art algorithms and relatively low accuracy of algorithm selection the accuracy of the semantic segmentation can be improved by 2\%.