Finding the Optimal Network Depth in Classification Tasks

17 Apr 2020Bartosz WójcikMaciej WołczykKlaudia BałazyJacek Tabor

We develop a fast end-to-end method for training lightweight neural networks using multiple classifier heads. By allowing the model to determine the importance of each head and rewarding the choice of a single shallow classifier, we are able to detect and remove unneeded components of the network... (read more)

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.