A Supervised Neural Autoregressive Topic Model for Simultaneous Image Classification and Annotation

TL;DR

This paper introduces SupDocNADE, a supervised neural autoregressive model that enhances scene recognition and annotation by integrating label information and spatial data, outperforming traditional topic models.

Contribution

The paper presents SupDocNADE, a novel supervised extension of DocNADE, tailored for visual scene modeling and capable of simultaneous classification and annotation.

Findings

SupDocNADE outperforms supervised LDA on multiple datasets.

Incorporating spatial and annotation info improves model accuracy.

Model achieves state-of-the-art results in scene recognition and annotation.

Abstract

Topic modeling based on latent Dirichlet allocation (LDA) has been a framework of choice to perform scene recognition and annotation. Recently, a new type of topic model called the Document Neural Autoregressive Distribution Estimator (DocNADE) was proposed and demonstrated state-of-the-art performance for document modeling. In this work, we show how to successfully apply and extend this model to the context of visual scene modeling. Specifically, we propose SupDocNADE, a supervised extension of DocNADE, that increases the discriminative power of the hidden topic features by incorporating label information into the training objective of the model. We also describe how to leverage information about the spatial position of the visual words and how to embed additional image annotations, so as to simultaneously perform image classification and annotation. We test our model on the Scene15, LabelMe and UIUC-Sports datasets and show that it compares favorably to other topic models such as the supervised variant of LDA.