Channelexplorer: Visualizing Cnn Activation Channels For Exploring Class Separability

Deep neural networks (DNNs) achieve state-of-the-art performance in many vision tasks, yet understanding their internal behavior remains challenging, particularly how different layers and activation channels contribute to class separability. We introduce ChannelExplorer, an interactive visual analytics tool for analyzing image-based outputs across model layers, emphasizing data-driven insights over architecture analysis for exploring class separability. ChannelExplorer summarizes activations across layers and visualizes them using three primary coordinated views: a Scatterplot View to reveal inter- and intra-class confusion, a Jaccard Similarity View to quantify activation overlap, and a Heatmap View to inspect activation channel patterns. Our technique supports diverse model architectures, including CNNs, GANs, ResNet and Stable Diffusion models. We demonstrate the capabilities of ChannelExplorer through four use-case scenarios: (1) generating class hierarchy in ImageNet, (2) finding mislabeled images, (3) identifying activation channel contributions, and(4) locating latent states’ position in Stable Diffusion model. Finally, we evaluate the tool with expert users.

Rahat Zaman, Bei Wang, and Paul Rosen. Channelexplorer: Visualizing Cnn Activation Channels For Exploring Class Separability. IEEE Transactions on Visualization and Computer Graphics (to appear), 2026.

@article{zaman2026cnn,
  title = {ChannelExplorer: Visualizing CNN Activation Channels for Exploring Class
    Separability},
  author = {Zaman, Rahat and Wang, Bei and Rosen, Paul},
  journal = {IEEE Transactions on Visualization and Computer Graphics  (to appear)},
  year = {2026},
  abstract = {Deep neural networks (DNNs) achieve state-of-the-art performance in many
    vision tasks, yet understanding their internal behavior remains challenging,
    particularly how different layers and activation channels contribute to class
    separability. We introduce ChannelExplorer, an interactive visual analytics tool for
    analyzing image-based outputs across model layers, emphasizing data-driven insights over
    architecture analysis for exploring class separability. ChannelExplorer summarizes
    activations across layers and visualizes them using three primary coordinated views: a
    Scatterplot View to reveal inter- and intra-class confusion, a Jaccard Similarity View
    to quantify activation overlap, and a Heatmap View to inspect activation channel
    patterns. Our technique supports diverse model architectures, including CNNs, GANs,
    ResNet and Stable Diffusion models. We demonstrate the capabilities of ChannelExplorer
    through four use-case scenarios: (1) generating class hierarchy in ImageNet, (2) finding
    mislabeled images, (3) identifying activation channel contributions, and(4) locating
    latent states' position in Stable Diffusion model. Finally, we evaluate the tool with
    expert users.}
}