A GENERAL PARAMETRIZATION FRAMEWORK FOR PAIRWISE MARKOV MODELS: AN APPLICATION TO UNSUPERVISED IMAGE SEGMENTATION

Hugo Gangloff (1, 2, 3, 4) , Katherine Morales (3, 1, 2) , Yohan Petetin (3, 1, 2)

1 IP Paris - Institut Polytechnique de Paris
2 TSP - CITI - Communications, Images et Traitement de l'Information
3 TIPIC-SAMOVAR - Traitement de l'Information Pour Images et Communications
4 MIA Paris-Saclay - Mathématiques et Informatique Appliquées

Probabilistic graphical models such as Hidden Markov models have found many applications in signal processing. In this paper, we focus on a particular extension of these models, the Pairwise Markov models. We propose a general parametrization of the probability distributions describing the Pairwise Markov models which enables us to combine them with recent architectures from machine learning such as deep neural networks. In order to evaluate the power of these combined architectures, we focus on the unsupervised image segmentation problem which is particularly challenging and we propose a new parameter estimation algorithm. We show that our models with their associated estimation algorithm outperforms the classical probabilistic models for the task of unsupervised image segmentation.

Mots clés: Deep neural networks; Image segmentation; Pairwise Markov chains; Expectation-maximization

Domaines: Statistiques [stat]; Traitement du signal et de l'image [eess.SP]; Applications [stat.AP]; Méthodologie [stat.ME]; Machine Learning [stat.ML]

Hugo Gangloff, Katherine Morales, Yohan Petetin. A GENERAL PARAMETRIZATION FRAMEWORK FOR PAIRWISE MARKOV MODELS: AN APPLICATION TO UNSUPERVISED IMAGE SEGMENTATION. 2021. ⟨hal-03181237v2⟩