Back in March, we open-sourced our implementation of “Fast Dense Feature Extraction with CNN’s that have Pooling or Striding Layers”, Although not broadly known, The 2017 BMVC published paper offers an efficient and elegant solution on how to avoid computational redundancy when using patch based Convolution Neural networks. So in this post I’ll explain how the model works and show how to use it in a real applications.
I’ll cover two things: First, an overview of the method named “Fast Dense Feature Extraction with CNN’s that have Pooling or Striding Layers”. And, second, how to use this approach on an existing trained patch network to speed up inference time.