A3B2 introduces an adaptive asymmetric adapter with uncertainty-aware dampening to reduce branch bias in few-shot vision-language image classification and outperforms standard adapter and prompt methods.
The second term penalizes large updates and is non-negative, hence: ∥∇V(x) ℓ′∥ ≤ ∥∇ V(x) ℓ∥
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A$_3$B$_2$: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning
A3B2 introduces an adaptive asymmetric adapter with uncertainty-aware dampening to reduce branch bias in few-shot vision-language image classification and outperforms standard adapter and prompt methods.