AI Dynamics

Global AI News Aggregator

CLIP Vision Model Bias: Skin Recognition and Context Understanding

Some interesting examples: In this image and a few others, CLIP appears to associate bare skin with "embarrassment". LLAVA and Captions + GPT don't, seeming to reason over the location and context.

→ View original post on X — @petitegeek,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *