Model Cascades for Efficient Image Search

03/27/2023
by   Robert Hönig, et al.
0

Modern neural encoders offer unprecedented text-image retrieval (TIR) accuracy. However, their high computational cost impedes an adoption to large-scale image searches. We propose a novel image ranking algorithm that uses a cascade of increasingly powerful neural encoders to progressively filter images by how well they match a given text. Our algorithm reduces lifetime TIR costs by over 3x.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset