Network Bending: Manipulating The Inner Representations of Deep Generative Models

We introduce a new framework for interacting with and manipulating deep generative models that we call network bending. We present a comprehensive set of deterministic transformations that can be inserted as distinct layers into the computational graph of a trained generative neural network and applied during inference. In addition, we present a novel algorithm for clustering features based on their spatial activation maps. This allows features to be grouped together based on spatial similarity in an unsupervised fashion. This results in the meaningful manipulation of sets of features that correspond to the generation of a broad array of semantically significant aspects of the generated images. We demonstrate these transformations on the official pre-trained StyleGAN2 model trained on the FFHQ dataset. In doing so, we lay the groundwork for future interactive multimedia systems where the inner representation of deep generative models are manipulated for greater creative expression, whilst also increasing our understanding of how such "black-box systems" can be more meaningfully interpreted.

Amplifying The Uncanny

Deep neural networks have become remarkably good at producing realistic deepfakes, images of people that are (to the untrained eye) indistinguishable from real images. These 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 and instead optimising the system to generate images that it sees as being fake. Maximising the unlikelihood of the data and in turn, amplifying the uncanny nature of these machine hallucinations.

Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks

We propose a computational framework to learn stylisation patterns from example drawings or writings, and then generate new trajectories that possess similar stylistic qualities. We particularly focus on the generation and stylisation of trajectories that are similar to the ones that can be seen in calligraphy and graffiti art. Our system is able to extract and learn dynamic and visual qualities from a small number of user defined examples which can be recorded with a digitiser device, such as a tablet, mouse or motion capture sensors. Our system is then able to transform new user drawn traces to be kinematically and stylistically similar to the training examples. We implement the system using a Recurrent Mixture Density Network (RMDN) combined with a representation given by the parameters of the Sigma Lognormal model, a physiologically plausible model of movement that has been shown to closely reproduce the velocity and trace of human handwriting gestures.