Partial Membership Latent Dirichlet Allocation

TL;DR

The paper introduces PM-LDA, a novel topic model that allows visual words to have partial memberships across multiple topics, enabling more flexible and accurate image segmentation especially in transitional regions.

Contribution

It proposes the PM-LDA model and an estimation algorithm, extending traditional topic models to handle soft segmentation in imagery.

Findings

PM-LDA produces both crisp and soft segmentations.

It outperforms previous models on visual and sonar imagery.

The model effectively captures transitional regions in images.

Abstract

Topic models (e.g., pLSA, LDA, sLDA) have been widely used for segmenting imagery. However, these models are confined to crisp segmentation, forcing a visual word (i.e., an image patch) to belong to one and only one topic. Yet, there are many images in which some regions cannot be assigned a crisp categorical label (e.g., transition regions between a foggy sky and the ground or between sand and water at a beach). In these cases, a visual word is best represented with partial memberships across multiple topics. To address this, we present a partial membership latent Dirichlet allocation (PM-LDA) model and an associated parameter estimation algorithm. This model can be useful for imagery where a visual word may be a mixture of multiple topics. Experimental results on visual and sonar imagery show that PM-LDA can produce both crisp and soft semantic image segmentations; a capability previous topic modeling methods do not have.