Saliency-Aware Projection Usability Enhancement for Dimensionality Reduction through Generative Models

Dimensionality reduction (DR), also known as projection, is one of the most commonly used methods for visualizing high-dimensional data. Despite its effectiveness in handling large datasets with high dimensions, users often face the challenge of tuning the parameters for optimal performance. Additionally, due to the lack of intuitive standards, users often struggle to quickly identify satisfactory results from the vast number of possible outcomes. Therefore, enhancing the usability of DR algorithms is an urgent problem that needs to be addressed. In this paper, we present a method based on generative models aimed at circumventing the parameter tuning process for DR. Furthermore, to provide users with valid recommendations, we introduce mixed quality metrics based on visual saliency for visualizing DR results. These quality metrics are mapped to a continuous latent space constructed by the generative model using interpolation. We demonstrate the validity and effectiveness of our method through a series of quantitative experiments. Subsequently, we develop a visual interface that combines the proposed method and metrics. The evaluation results demonstrate that our method can quickly recommend good DR results, leading to a more user-friendly and efficient visualization analysis experience.