Visualizing CNNs (Part 1)

Two options:

• visualizing the activation maps and convolutional layers
• taking filter from convolutional layers and constructing images that maximize their activations, google researchers get creative with this and designed technique called deep dreams
  • say we have picture of tree, investigate filter for detecting a building, end up creating image that looks like some sort of tree or building hybrid

Visualizing CNNs (Part 2)

• based on paper (opens new window) by Zeiler and Fergus, visualization using this toolbox (opens new window).
  • Layer 1 - pick out very simple shapes and patterns like lines and blobs
  • Layer 2 - circle, stripes and rectangle
  • Layer 3 - complex combinations of features from the second layer
  • Layer 4 - continue progression
  • Layer 5 - classification