Latent Dirichlet Allocation Models for Image Classification

99 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces (2017, neutral): “Supervised variations of LDA are presented in [30, 42, 28] where the discovered topics are driven by the semantic regularities of interest for the classification task.”
Saliency-Guided Unsupervised Feature Learning for Scene Classification (2015, methodology): “Under these models, each image is represented as a finite mixture of an intermediate set of topics, which are expected to summarize the scene information [9].”
Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images (2015, background): “This is because the objective is the sum of visual words and label likelihoods, and visual words vastly outnumber annotations, thus dominating the result [51].”
Generative Adversarial Networks (2021, unknown): “Latent Dirichlet Allocation [9] (LDA) and the Gaussian Mixture Model [10] (GMM) are two more examples of generative models.”
Scene Classification via a Gradient Boosting Random Convolutional Network Framework (2016, methodology): “Under these models, each image is represented as a finite mixture of an intermediate set of topics, which are expected to summarize the scene information [9].”