Generative Adversarial Network (GAN) is being widely adopted in numerous application areas, such as data preprocessing, image editing, and creativity support. However, GAN's 'black box' nature prevents non-expert users from controlling what data a model generates, spawning a plethora of prior work that focused on algorithm-driven approaches to automatically extract editing directions to control GAN. Complementarily, we propose a GANzilla---a user-driven tool that empowers a user with the classic scatter/gather technique to iteratively discover directions to meet their editing intents. In a work session with 12 participants, GANzilla users were able to discover directions that (i) edited images to match provided examples (closed-ended tasks) and that (ii) met a high-level goal, e.g., making the face happier, while showing diversity across individuals (open-ended tasks).
https://doi.org/10.1145/3526113.3545638
The ACM Symposium on User Interface Software and Technology