Note on CNN Interpretability

2 major way of interpreting CNN

  • Feature visualization: See what a hidden neuron is interested in
  • Attribution: See what part of image activate a filter or detector

Activation Atlas

These works try to find a tool kits for visualizing DeepNN and building up a human-computer interface of DeepNN.

https://distill.pub/2019/activation-atlas/

https://distill.pub/2018/building-blocks/

https://distill.pub/2017/feature-visualization/