Proposal of New Activation Function in Deep Image Prior
Ryo Segawa, Hitoshi Hayashi, Shohei Fujii · IEEJ Transactions on Electrical and Electronic Engineering · 2020
We propose a new activation function and verify its performance in a deep image prior network. The new activation function is RSwish, which is Swish with a random slope for x < 0 assuming that the input value of the activation function is x. In addition, we manipulate the probability of the random number and observe the effect. As a result, we found that RSwish can perform better than Swish by manipulating probabilities according to the degree of color change in the image. © 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.