1 code implementation • 5 May 2021 • Dmitry Nikulin, Roman Suvorov, Aleksei Ivakhnenko, Victor Lempitsky
The use of perceptual loss however incurs repeated forward-backward passes in a large image classification network as well as a considerable memory overhead required to store the activations of this network.
1 code implementation • 7 Aug 2019 • Dmitry Nikulin, Anastasia Ianina, Vladimir Aliev, Sergey Nikolenko
We show experimentally that a network with an FLS module exhibits performance similar to the baseline (i. e., it is "free", with no performance cost) and can be used as a drop-in replacement for reinforcement learning agents.