Visual Search with OpenAI CLIP
SentenceTransformers provides models that allow to embed images and text into the same vector space. This allows to find similar images as well as to implement image search. We can define a query using text or using a reference image.
Some examples:
19-Sep-2022
Serge Retkowsky | serge.retkowsky@microsoft.com | https://www.linkedin.com/in/serger/