Amplifying The Uncanny

TL;DR

This paper explores a novel approach to deepfake generation by inverting the typical training process, optimizing neural networks to produce images the system predicts as fake, thereby amplifying their uncanny aesthetic.

Contribution

It introduces a new method that reverses the usual deepfake training, emphasizing the creation of uncanny images through maximized unlikelihood.

Findings

Generated images exhibit heightened uncanny qualities.

Inverted optimization enhances the surreal and unsettling aspects.

The approach offers a new artistic perspective on machine hallucinations.

Abstract

Deep neural networks have become remarkably good at producing realistic deepfakes, images of people that (to the untrained eye) are indistinguishable from real images. Deepfakes are produced by algorithms that learn to distinguish between real and fake images and are optimised to generate samples that the system deems realistic. This paper, and the resulting series of artworks Being Foiled explore the aesthetic outcome of inverting this process, instead optimising the system to generate images that it predicts as being fake. This maximises the unlikelihood of the data and in turn, amplifies the uncanny nature of these machine hallucinations.