Participate In a GAN Detection Study

Study 1 – Paired Aerial Image Detection

Looking for a Participants to participate in a quick (5-15 mins) online GAN detection study.

I am looking for participants to take part in my short online study on detecting GAN generated synthetic aerial images. We have used Generative Adversarial Networks (GANs) to create these.
I am looking for participants from all backgrounds, as well as those who have specific experience in dealing with either Earth Observation Data (Satellite aerial images) or GAN-generated images.

Purpose: To assess the difficulty in the task of distinguishing GAN generated fake images from real satellite photos of rural and urban environments.  This is part of a larger PhD project looking at the generation and detection of fake earth observation data.

Who can participate? This is open to anyone who would like to take part, although the involvement of people with experience dealing with related image data (e.g. satellite images, GAN images) is of particular interest.

Commitment: The study should take between 5-15 minutes to complete and is hosted online on pavlovia.org

Study URL: https://run.pavlovia.org/Matty0512/realfakev2/html

Study 2 – Identifying visual fingerprints of GAN generated aerial images

Looking for a Participants to participate in a longer (10-25 mins) online GAN detection study.

In this second study I am again looking for participants for a study involving the detection of GAN generated aerial images. Participants from all backgrounds are encouraged to participate. The study involves an anonymous survey about experience and occupation on Google forms and

Purpose: To identify the parts of a syntheised image which visually distinguish it as being unrealistic. The study looks to establish what differences there are in detection and detection behaviour between participants with varying levels of experience in handling aerial images or GAN data.

Who can participate? This is open to anyone who would like to take part, although the involvement of people with experience dealing with related image data (e.g. satellite images, GAN images) is of particular interest.

Commitment: Participants can take part in as much or as little as they would like (although it is encouraged to complete the full task.) As this study is hosted on Zooniverse.org participants may save their progress and complete in their own time.

Study URL: https://formfaca.de/sm/_kBsk76eo

For any additional information or queries please feel free to contact me,
Matthew Yates


Create your website with WordPress.com
Get started
%d bloggers like this: