A proposed unified regularizer for CLIP prompt learning, combining Fisher information and confidence penalties, is reported to improve few-shot accuracy and calibration, but the core combined method is not tested and key definitions conflict.
Align your prompts: Test-time prompting with distribution align- ment for zero-shot generalization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Confidence-calibrated covariate shift correction for few-shot classification in Vision-Language Models
A proposed unified regularizer for CLIP prompt learning, combining Fisher information and confidence penalties, is reported to improve few-shot accuracy and calibration, but the core combined method is not tested and key definitions conflict.