Lightweight GANs

Generative Adversarial Networks (GANs) show outstanding performance in various fields such as image generation, image editing, and image inpainting. However, GANs are generally unfriendly to ordinary users because they are not efficient, such as requiring a lot of data or requiring a lot of computational costs. Although compression methods for GANs have been explored to address these problems, previous works still have performance degradation due to the unstable nature of GANs. We believe that the performance degradation of compressed GANs can be mitigated by maintaining the stability of GANs. In this project, we research suitable and stable compression methods for generative models and build the baseline for comparing the performance of various state-of-the-art compression methods. 

This project is suitable for (but not limited to) students majoring in electrical engineering, computer science, industrial engineering, and mathematics. Ideally, students in their third year or higher are preferred. Basic English skills for reading and presenting papers and proficiency in Python programming are required. Otherwise, it will be very difficult to proceed with the project. Students who have experience with deep learning projects or have read papers on the topic are preferred. If they have experience working with generative models, it would be even better.

Supervisors

(If you are interested, please contact the supervisor below)


Feel like you want to explore other projects? Go and look for the list here: Student (Intern) projects