Dear FOMO25 Organizers,
I have a question regarding the finetuning approach. Are we allowed to retrain the entire pre-trained unsupervised model (starting from a common checkpoint) for each downstream task, or must we keep the encoder frozen and only train specific decoders/heads using the learned representations?
I hope my question is clear.
Kind regards,
Jaume
Created by Jaume Banus Cobo jbanusco Hello,
You are allowed to do full end-to-end finetuning. Looking forward to your submissions!
Best, Asbjørn
Drop files to upload
Clarification on finetuning approach page is loading…