Year: 2019
Type: preprint
Abstract: In response to the development of recent efficient dense layers, this paper shows that something as simple as replacing linear components in pointwise convolutions with structured linear decompositions also produces substantial gains in the efficiency/accuracy tradeoff. Pointwise convolutions are fully connected layers and are thus prepared for replacement by structured transforms. Networks using such layers are able to learn the same tasks as those using standard convolutions, and provide Pareto-optimal benefits in efficiency/accuracy, both in terms of computation (mult-adds) and parameter count (and hence memory). Code is available at https://github.com/BayesWatch/deficient-efficient.
Source: arXiv (Cornell University)
Authors: Gray, Gavin, Crowley, Elliot J., Storkey, Amos
Institution: University of Edinburgh
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2947776571