Covariance-aware scoring proposed as geometric correction for vision-language test-time adaptation
A new arXiv paper introduces covariance-aware scoring, a geometric correction method for test-time adaptation of vision-language models like CLIP under distribution shifts, without labels or source data.
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-11-03 05:00 · arXiv cs.CV
Covariance-aware Scoring: A Geometric Correction for Vision-Language Test-Time Adaptation