# Finite State Machines for Semantic Scene Parsing and Segmentation

## TL;DR

This paper presents a novel stochastic inference framework using finite state machines for semantic scene annotation and segmentation, enabling complex operations like reordering and label dependency modeling.

## Contribution

It introduces a generative FSM-based approach that encodes annotation lattices and integrates multiple operations for improved scene parsing.

## Key findings

- Effective scene annotation and segmentation
- New FSM operations for reordering and label dependencies
- Unified framework for multiple inference tasks

## Abstract

We introduce in this work a novel stochastic inference process, for scene annotation and object class segmentation, based on finite state machines (FSMs). The design principle of our framework is generative and based on building, for a given scene, finite state machines that encode annotation lattices, and inference consists in finding and scoring the best configurations in these lattices. Different novel operations are defined using our FSM framework including reordering, segmentation, visual transduction, and label dependency modeling. All these operations are combined together in order to achieve annotation as well as object class segmentation.