Visualizing Semiotics in Generative Adversarial Networks
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.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeFormGenerative Adversarial NetworkSimilar Papers 제목 키워드 기반
Semantic interoperability based on the European Materials and Modelling Ontology and its ontological paradigm: Mereosemiotics
The European Materials and Modelling Ontology (EMMO) has recently been advanced in the computational molecular engineering and multiscale modelling communities as a top-level ontology, aiming to support semantic interope…
Data IntegrationSemiotic Aggregation in Deep Learning
Convolutional neural networks utilize a hierarchy of neural network layers. The statistical aspects of information concentration in successive layers can bring an insight into the feature abstraction process. We analyze …
Deep LearningVisualizing chest X-ray dataset biases using GANs
Recent work demonstrates that images from various chest X-ray datasets contain visual features that are strongly correlated with protected demographic attributes like race and gender. This finding raises issues of fairne…
FairnessSampling Generative Networks
We introduce several techniques for sampling and visualizing the latent spaces of generative models. Replacing linear interpolation with spherical linear interpolation prevents diverging from a model's prior distribution…
AttributeBinary ClassificationData AugmentationGeneral Classification+1AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
In this paper, we propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation. With a novel attentional generative networ…
Generative Adversarial NetworkImage GenerationImage-text matchingText Matching+2