Skip to content

Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning - McDonnell et al (2024) - https://arxiv.org/abs/2403.07356

License

Notifications You must be signed in to change notification settings

McDonnell-Research-Lab/premonition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning

Official code repository for:

Mark D. McDonnell, Dong Gong, Ehsan Abbasnejad, Anton van den Hengel (2024). "Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning." Available at https://arxiv.org/abs/2403.07356.

Contact: mark.mcdonnell@adelaide.edu.au

Currently, we provide demo jupyter notebooks that illustrate how a realm description prompt is converted to synthetic datasets for Premonition's supervised pre-training.

  • Notebooks/Get_SD_Prompts_From_Realm
  • Notebooks/Get_Images_from_Prompts

About

Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning - McDonnell et al (2024) - https://arxiv.org/abs/2403.07356

Topics

Resources

License

Stars

Watchers

Forks