Skip to content

Latest commit

 

History

History
16 lines (15 loc) · 1.24 KB

dl_07.md

File metadata and controls

16 lines (15 loc) · 1.24 KB

Visualizing and understanding convolutional networks

Matthew D. Zeiler, Rob Fergus (2013)

Key points

  • Novel visualization technique to understand representations learned by intermediate layers of a CNN
    • Propose architecture changes based on this --> resulting model performs and generalizes better!
  • DeConvNet used for this: feature activations mapped back to input space by setting other activations = 0, and subsequently unpooling, rectification, filtering
    • Unpooling: approximated using switch variables to remember highest input activation locations --> visualizations are image-specific!
    • Rectification: pass through ReLU
    • Filtering: convolving reconstructed signal with transpose of convolutional layer filters
  • Lower layers converge within a few epochs, while upper layers need more epochs to develop
  • Small transformations in the image have a larger effect on lower layers
    • Model is fairly stable to translation + scaling, not rotation
  • Drop in activities in feature map when object is occluded:
    • CNNs implicitly learn correspondence between different parts, as shown through lower scores when occluding the same object for various poses
  • Minimum depth of model, rather than any individual section, is vital to performance!