Discovering Latent Topics by Gaussian Latent Dirichlet Allocation and Spectral Clustering

Today, diversifying the retrieval results of a certain query will improve customers' search efficiency. Showing the multiple aspects of information provides users an overview of the object, which helps them fast target their demands. To discover aspects, research focuses on generating image clusters from initially retrieved results. As an effective approach, latent Dirichlet allocation (LDA) has been proved to have good performance on discovering high-level topics. However, traditional LDA is designed to process textual words, and it needs the input as discrete data. When we apply this algorithm to process continuous visual images, a common solution is to quantize the continuous features into discrete form by a bag-of-visual-words algorithm. During this process, quantization error will lead to information that inevitably is lost. To construct a topic model with complete visual information, this work applies Gaussian latent Dirichlet allocation (GLDA) on the diversity issue of image retrieval. In this model, traditional multinomial distribution is substituted with Gaussian distribution to model continuous visual features. In addition, we propose a two-phase spectral clustering strategy, called dual spectral clustering, to generate clusters from region level to image level. The experiments on the challenging landmarks of the DIV400 database show that our proposal improves relevance and diversity by about 10% compared to traditional topic models.