Interactive Visual Study of Multiple Attributes Learning Model of X-Ray Scattering Images

TL;DR

This paper introduces an interactive visualization system enabling domain scientists to explore and analyze multiple attribute learning models applied to x-ray scattering images, facilitating model improvement and data quality assessment.

Contribution

It presents a novel interactive visualization tool tailored for x-ray scattering image classification, addressing a gap in existing deep learning visualization tools.

Findings

System effectively helps identify questionable labels and outliers.

Case studies validate its usefulness for model analysis.

Feedback indicates improved understanding of attribute relationships.

Abstract

Existing interactive visualization tools for deep learning are mostly applied to the training, debugging, and refinement of neural network models working on natural images. However, visual analytics tools are lacking for the specific application of x-ray image classification with multiple structural attributes. In this paper, we present an interactive system for domain scientists to visually study the multiple attributes learning models applied to x-ray scattering images. It allows domain scientists to interactively explore this important type of scientific images in embedded spaces that are defined on the model prediction output, the actual labels, and the discovered feature space of neural networks. Users are allowed to flexibly select instance images, their clusters, and compare them regarding the specified visual representation of attributes. The exploration is guided by the manifestation of model performance related to mutual relationships among attributes, which often affect the learning accuracy and effectiveness. The system thus supports domain scientists to improve the training dataset and model, find questionable attributes labels, and identify outlier images or spurious data clusters. Case studies and scientists feedback demonstrate its functionalities and usefulness.