Active Divergence with Generative Deep Learning -- A Survey and Taxonomy
arXiv:2107.05599
Abstract
Generative deep learning systems offer powerful tools for artefact generation, given their ability to model distributions of data and generate high-fidelity results. In the context of computational creativity, however, a major shortcoming is that they are unable to explicitly diverge from the training data in creative ways and are limited to fitting the target data distribution. To address these limitations, there have been a growing number of approaches for optimising, hacking and rewriting these models in order to actively diverge from the training data. We present a taxonomy and comprehensive survey of the state of the art of active divergence techniques, highlighting the potential for computational creativity researchers to advance these methods and use deep generative models in truly creative systems.
References in corpus (12)
- Learning Transferable Visual Models From Natural Language Supervision
- NICE: Non-linear Independent Components Estimation
- Zero-Shot Text-to-Image Generation
- Illuminating search spaces by mapping elites
- CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms
- Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domains
- Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
- Real-time interactive sequence generation and control with Recurrent Neural Network ensembles
- Automating Generative Deep Learning for Artistic Purposes: Challenges and Opportunities
- Transforming the output of GANs by fine-tuning them with features from different datasets
- Generating Novel Glyph without Human Data by Learning to Communicate
- Searching for an (un)stable equilibrium: experiments in training generative models without data