3min chapter

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis cover image

E6: The Computer Vision Revolution with Junnan Li and Dongxu Li of BLIP and BLIP2

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

CHAPTER

Is Blip 2 a Better Training Model?

There's so much noise in there. Got a lot of things that are just like, what an awesome day. And that doesn't really line up with what's in the image. It sounds like in your case to create a captioner, this was working against you. So did you just go through the giant data set and just kind of filter out things with low similarity score and work from that? Yeah, exactly, like what you described. We just go through all the examples and filter out those data, not align those image. The original Blip model is like one to two gigabytes downloaded, if I recall correctly. But because we keep it frozen, during the friction, it

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode