Italian Chapter Conference 2021 - Smart Tools and Apps in Graphics

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2633100

Browse

Browsing Italian Chapter Conference 2021 - Smart Tools and Apps in Graphics by Subject "centered computing → Visual analytics"

Now showing 1 - 1 of 1
  • No Thumbnail Available
    Item
    An Information-theoretic Visual Analysis Framework for Convolutional Neural Networks
    (The Eurographics Association, 2021) Shen, Jingyi; Shen, Han-Wei; Frosini, Patrizio and Giorgi, Daniela and Melzi, Simone and Rodolà, Emanuele
    Despite the great success of Convolutional Neural Networks (CNNs) in Computer Vision and Natural Language Processing, the working mechanism behind CNNs is still under extensive discussion and research. Driven by strong demand for the theoretical explanation of neural networks, some researchers utilize information theory to provide insight into the black-box model. However, to the best of our knowledge, employing information theory to quantitatively analyze and qualitatively visualize neural networks has not been extensively studied in the visualization community. In this paper, we combine information entropies and visualization techniques to shed light on how CNN works. Specifically, we first introduce a data model to organize the data that can be extracted from CNN models. Then we propose two ways to calculate entropy under different circumstances. To provide a fundamental understanding of the basic building blocks of CNNs (e.g., convolutional layers, pooling layers, normalization layers) from an information-theoretic perspective, we develop a visual analysis system, CNNSlicer. CNNSlicer allows users to interactively explore the amount of information changes inside the model. With case studies on the widely used benchmark datasets (MNIST and CIFAR-10), we demonstrate the effectiveness of our system in opening the black-box of CNNs.