I haven’t tried this yet, excited to see how it can do segmentation by outputtin... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		maciejgryka on May 15, 2024 \| parent \| context \| favorite \| on: PaliGemma: Open-Source Multimodal Model by Google I haven’t tried this yet, excited to see how it can do segmentation by outputting series of coordinates! That's something I just assumed transformers will generally be bad at.

yeldarb on May 15, 2024 [–]

How it does this is really cool. It’s got a VAE decoder. Reminds me a lot of how SAM works.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact