And the Bit Goes Down: Revisiting the Quantization of Neural Networks

ICLR 2020 Pierre StockArmand JoulinRémi GribonvalBenjamin GrahamHervé Jégou

In this paper, we address the problem of reducing the memory footprint of convolutional network architectures. We introduce a vector quantization method that aims at preserving the quality of the reconstruction of the network outputs rather than its weights... (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.

Methods used in the Paper