A$_3$B$_2$: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Yiyun, Jiang, Zhonghua, Han, Wenkang, Li, Kunxi, Xu, Mingjing, Yao, Chang, Chen, Jingyuan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918505268379648
author Zhou, Yiyun
Jiang, Zhonghua
Han, Wenkang
Li, Kunxi
Xu, Mingjing
Yao, Chang
Chen, Jingyuan
author_facet Zhou, Yiyun
Jiang, Zhonghua
Han, Wenkang
Li, Kunxi
Xu, Mingjing
Yao, Chang
Chen, Jingyuan
contents Efficient transfer learning methods for large-scale vision-language models ($e.g.$, CLIP) enable strong few-shot transfer, yet existing adaptation methods follow a fixed fine-tuning paradigm that implicitly assumes a uniform importance of the image and text branches, which has not been systematically studied in image classification. Through extensive analysis, we reveal a Branch Bias issue in vision-language image classification: adapting the image encoder does not always improve performance under out-of-distribution settings. Motivated by this observation, we propose A$_3$B$_2$, an Adaptive Asymmetric Adapter that alleviates Branch Bias in few-shot learning. A$_3$B$_2$ introduces Uncertainty-Aware Adapter Dampening (UAAD), which automatically suppresses image-branch adaptation when prediction uncertainty is high, enabling soft and data-driven control without manual intervention. Architecturally, A$_3$B$_2$ adopts a lightweight asymmetric design inspired by mixture-of-experts with Load Balancing Regularization. Extensive experiments on three few-shot image classification tasks across 11 datasets demonstrate that A$_3$B$_2$ consistently outperforms 11 competitive prompt- and adapter-based baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13161
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A$_3$B$_2$: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning
Zhou, Yiyun
Jiang, Zhonghua
Han, Wenkang
Li, Kunxi
Xu, Mingjing
Yao, Chang
Chen, Jingyuan
Computer Vision and Pattern Recognition
Machine Learning
Efficient transfer learning methods for large-scale vision-language models ($e.g.$, CLIP) enable strong few-shot transfer, yet existing adaptation methods follow a fixed fine-tuning paradigm that implicitly assumes a uniform importance of the image and text branches, which has not been systematically studied in image classification. Through extensive analysis, we reveal a Branch Bias issue in vision-language image classification: adapting the image encoder does not always improve performance under out-of-distribution settings. Motivated by this observation, we propose A$_3$B$_2$, an Adaptive Asymmetric Adapter that alleviates Branch Bias in few-shot learning. A$_3$B$_2$ introduces Uncertainty-Aware Adapter Dampening (UAAD), which automatically suppresses image-branch adaptation when prediction uncertainty is high, enabling soft and data-driven control without manual intervention. Architecturally, A$_3$B$_2$ adopts a lightweight asymmetric design inspired by mixture-of-experts with Load Balancing Regularization. Extensive experiments on three few-shot image classification tasks across 11 datasets demonstrate that A$_3$B$_2$ consistently outperforms 11 competitive prompt- and adapter-based baselines.
title A$_3$B$_2$: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2605.13161