The power of pictures: using ML assisted image generation to engage the crowd in complex socioscientific problems
arXiv:2010.12324
Abstract
Human-computer image generation using Generative Adversarial Networks (GANs) is becoming a well-established methodology for casual entertainment and open artistic exploration. Here, we take the interaction a step further by weaving in carefully structured design elements to transform the activity of ML-assisted imaged generation into a catalyst for large-scale popular dialogue on complex socioscientific problems such as the United Nations Sustainable Development Goals (SDGs) and as a gateway for public participation in research.
References in corpus (8)
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Improved Techniques for Training GANs
- Outline Colorization through Tandem Adversarial Networks
- Neural Painters: A learned differentiable constraint for generating brushstroke paintings
- Machine learning based co-creative design framework
- Dialog on a canvas with a machine
- Transform the Set: Memory Attentive Generation of Guided and Unguided Image Collages
- crea.blender: A Neural Network-Based Image Generation Game to Assess Creativity