Dynamical Inference Lab
Dynamical Inference Lab
Home
Team
Research
Join us!
Outreach
Contact
Ori Press
Latest
RDumb: A Simple Approach that Questions Our Progress in Continual Test-Time Adaptation
RDumb is a simple baseline that periodically resets the model to its pretrained state, yet outperforms state-of-the-art continual …
Ori Press
,
Steffen Schneider
,
Matthias Kümmerer
,
Matthias Bethge
PDF
Code
Project
Cite
×