Visual embeddings from CLIP and other vision encoders encode ordinal attributes along linear directions, recoverable from as few as two extreme reference images, without full supervision.
Deep Learning for Instance Retrieval: A Survey
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
On the rankability of visual embeddings
Visual embeddings from CLIP and other vision encoders encode ordinal attributes along linear directions, recoverable from as few as two extreme reference images, without full supervision.