CNNComparator: Comparative Analytics of Convolutional Neural Networks

TL;DR

This paper introduces CNNComparator, a visual analytics system designed to compare different snapshots of CNN models at various training stages, helping researchers understand parameter changes and improve model training.

Contribution

It presents a novel visual analytics approach for comparing CNN snapshots, revealing insights into parameter evolution and training dynamics.

Findings

Effective comparison of CNN snapshots demonstrated in case study

Revealed relationships between parameters and model performance

Facilitated understanding of training process and model design

Abstract

Convolutional neural networks (CNNs) are widely used in many image recognition tasks due to their extraordinary performance. However, training a good CNN model can still be a challenging task. In a training process, a CNN model typically learns a large number of parameters over time, which usually results in different performance. Often, it is difficult to explore the relationships between the learned parameters and the model performance due to a large number of parameters and different random initializations. In this paper, we present a visual analytics approach to compare two different snapshots of a trained CNN model taken after different numbers of epochs, so as to provide some insight into the design or the training of a better CNN model. Our system compares snapshots by exploring the differences in operation parameters and the corresponding blob data at different levels. A case study has been conducted to demonstrate the effectiveness of our system.