CG-GAN: An Interactive Evolutionary GAN-Based Approach for Facial Composite Generation

Zaltron, Nicola; Zurlo, Luisa; Risi, Sebastian

doi:10.1609/aaai.v34i03.5637

Cited by 27 publications

(24 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was also deployed successfully for searching through the latent space of a WaveGAN for the purpose of augmenting datasets [21]. Further, LVE was used to give human users the ability to interactively evolve through a learned GAN space [3,31]. However, all the aforementioned methods focus on controlling the output of GANs by making it more interpretable and transparent.…”

Section: Gans and Controllabilitymentioning

confidence: 99%

Taming the Chaos: Exploring Graphical Input Vector Manipulation User Interfaces for GANs in a Musical Context

2021

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) are a widely used tool for generating highly realistic artificial data. As the output of these networks can show high diversity and novelty, GANs have the potential to be used as creative tools. However, using GANs in this context poses major challenges due to their unpredictability and lack of controllability, making it difficult for creative people to realize their artistic vision. To address this problem, we present two graphical user interfaces that visually order the (otherwise chaotic) latent input space of a GAN that was trained to generate drum samples. Further, these GUIs provide convergent search functions that allow users to fine-tune generated sounds. By doing so, we provide the ability to create sounds more purposefully to soundaffine users such as musicians or sound engineers. Additionally, we present the results of a user study that we conducted in order to explore our approach in accuracy-oriented and creative tasks. Our results indicate that usability and pragmatic qualities play a more important role for users than aesthetic-oriented aspects.Although not improving the accuracy within reproductive tasks, we observed that convergent search functions, if available, were used significantly more often than divergent/randomized search functions. CCS CONCEPTS• Human-centered computing → User interface design; Empirical studies in interaction design.

show abstract

Section: Gans and Controllabilitymentioning

confidence: 99%

Taming the Chaos: Exploring Graphical Input Vector Manipulation User Interfaces for GANs in a Musical Context

2021

View full text Add to dashboard Cite

show abstract

“…Such target-based evolution has been shown to be challenging with other indirect encodings [47]. In more recent work, Zaltron et al [50] extended the approach in Bontrager et al with the ability to freeze and manually edit certain features, allowing users to easily create facial composites.…”

Section: Latent Variable Evolutionmentioning

confidence: 99%

“…An alternative is interactive evolution, which can explore a search space with a human in the loop [3,10,40,50]. Interactive evolution allows a user to select whatever options are most appealing at the moment, allowing for serendipitous discovery of novel solutions without formalized domain knowledge.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Interactive evolution and exploration within latent level-design space of generative adversarial networks

Schrum

Gutierrez

Volz

et al. 2020

Proceedings of the 2020 Genetic and Evolutionary Computation Conference

Self Cite

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) are an emerging form of indirect encoding. The GAN is trained to induce a latent space on training data, and a real-valued evolutionary algorithm can search that latent space. Such Latent Variable Evolution (LVE) has recently been applied to game levels. However, it is hard for objective scores to capture level features that are appealing to players. Therefore, this paper introduces a tool for interactive LVE of tile-based levels for games. The tool also allows for direct exploration of the latent dimensions, and allows users to play discovered levels. The tool works for a variety of GAN models trained for both Super Mario Bros. and The Legend of Zelda, and is easily generalizable to other games. A user study shows that both the evolution and latent space exploration features are appreciated, with a slight preference for direct exploration, but combining these features allows users to discover even better levels. User feedback also indicates how this system could eventually grow into a commercial design tool, with the addition of a few enhancements.

show abstract

“…Thus, the randomness of the generated samples can be overcome. This so called Latent Vector Evolution (LVE) has been successfully employed for tasks like fingerprint-based biometric systems, creation of video games or facial composite generation [17]- [21]. The ability to generate samples in a targeted way makes LVE a promising approach to enhance datasets with data that is actually meaningful for the respective classification task.…”

Section: Related Workmentioning

confidence: 99%

An Evolutionary-based Generative Approach for Audio Data Augmentation

Mertes

Baird

Schiller

et al. 2020

2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)

View full text Add to dashboard Cite

In this paper, we introduce a novel framework to augment raw audio data for machine learning classification tasks. For the first part of our framework, we employ a generative adversarial network (GAN) to create new variants of the audio samples that are already existing in our source dataset for the classification task. In the second step, we then utilize an evolutionary algorithm to search the input domain space of the previously trained GAN, with respect to predefined characteristics of the generated audio. This way we are able to generate audio in a controlled manner that contributes to an improvement in classification performance of the original task. To validate our approach, we chose to test it on the task of soundscape classification. We show that our approach leads to a substantial improvement in classification results when compared to a training routine without data augmentation and training with uncontrolled data augmentation with GANs.

show abstract

CG-GAN: An Interactive Evolutionary GAN-Based Approach for Facial Composite Generation

Cited by 27 publications

References 14 publications

Taming the Chaos: Exploring Graphical Input Vector Manipulation User Interfaces for GANs in a Musical Context

Taming the Chaos: Exploring Graphical Input Vector Manipulation User Interfaces for GANs in a Musical Context

Interactive evolution and exploration within latent level-design space of generative adversarial networks

An Evolutionary-based Generative Approach for Audio Data Augmentation

Contact Info

Product

Resources

About