English

Fully Convolutional Fractional Scaling

Neural and Evolutionary Computing 2022-03-22 v1 Machine Learning

Abstract

We introduce a fully convolutional fractional scaling component, FCFS. Fully convolutional networks can be applied to any size input and previously did not support non-integer scaling. Our architecture is simple with an efficient single layer implementation. Examples and code implementations of three common scaling methods are published.

Keywords

Cite

@article{arxiv.2203.10670,
  title  = {Fully Convolutional Fractional Scaling},
  author = {Michael Soloveitchik and Michael Werman},
  journal= {arXiv preprint arXiv:2203.10670},
  year   = {2022}
}
R2 v1 2026-06-24T10:19:50.431Z