Anisotropic self-supervised vision representations degrade approximate nearest-neighbor retrieval performance while more isotropic ones with local purity improve it.
Global geometry is not enough for vision representations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geometric Analysis of Self-Supervised Vision Representations for Semantic Image Retrieval
Anisotropic self-supervised vision representations degrade approximate nearest-neighbor retrieval performance while more isotropic ones with local purity improve it.