A Visualization Method for Analyzing Data Domain Changes in CNN Networks and an Optimization Approach for Selecting Thresholds in Classification Tasks

This paper proposes a visualization method to intuitively reflect the training outcomes of models by visualizing the prediction results on datasets. It also demonstrates that employing data augmentation techniques, such as downsampling and Gaussian blur, can effectively enhance performance on cross-domain FAS tasks. Additionally, the paper introduces a methodology for setting threshold values based on the distribution of the training dataset.