Paper ID: 2203.10670

Fully Convolutional Fractional Scaling

Michael Soloveitchik, Michael Werman

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.

Submitted: Mar 20, 2022