AI Image Search: Perception Encoder vs. CLIP
Registration
About Event
Let's see how two powerful vision language models compare in a head-to-head matchup.
In this live session, Peter Robicheaux, Machine Learning Lead at Roboflow, will compare text-to-image search capabilities of CLIP and Perception Encoder.
You'll see a live demonstration of which model delivers more precise and relevant results based on a variety of search queries. We'll explore biases in the models, analyze performance differences, and see why you might want to implement Perception Encoder as a replacement for CLIP.
Every week we dive into the world of computer vision and explore new tools, interesting projects, and tutorials. This webinar is open to everyone, we hope to see you there!
We'll also make time at the end for open Q&A.