Visualizing Semiotics in Generative Adversarial Networks
This work addresses a novel challenge in generative AI for designers and artists by enabling control over abstract visual concepts, though it appears incremental as an extension of existing attribute manipulation techniques.
The paper tackles the problem of modifying abstract, non-physical properties like 'alertness' or 'futuristic' in images generated by Generative Adversarial Networks, demonstrating that such semiotic attributes can be controlled through an iterative method to aid design processes.
We perform a set of experiments to demonstrate that images generated using a Generative Adversarial Network can be modified using 'semiotics.' We show that just as physical attributes such as the hue and saturation of an image can be modified, so too can its non-physical, abstract properties using our method. For example, the design of a flight attendant's uniform may be modified to look more 'alert,' less 'austere,' or more 'practical.' The form of a house can be modified to appear more 'futuristic,' a car more 'friendly' a pair of sneakers, 'evil.' Our method uncovers latent visual iconography associated with the semiotic property of interest, enabling a process of visual form-finding using abstract concepts. Our approach is iterative and allows control over the degree of attribute presence and can be used to aid the design process to yield emergent visual concepts.