How Much Transfer Is Possible?

I feel like a lot of the fields of computer vision doesn't have that much data, and it's very hard to convince them to move their entire stack to transformers. So perhaps if you have large amounts of data from different domains, or say multiple time series domains, and you have a pre-trained model on that, then in your medical domain with small amount of data, that's what can be used to fine-tune them. I think it makes sense in academic research, or if you're opening eye going into the state of the art,. but you were talking about robustness in medical fields.

Transcript

Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!

Get the app