---
title: "A₃B₂: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning"
authors:
  - "Yiyun Zhou"
  - "Zhonghua Jiang"
  - "Wenkang Han"
  - "Kunxi Li"
  - "Mingjing Xu"
  - "Chang Yao"
  - "Jingyuan Chen"
doi: "10.24963/ijcai.2026/238"
url: "https://ijcai.org/proceedings/2026/238"
pdf: "https://ijcai.org/proceedings/2026/0238.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "2136-2144"
track: "Main Track"
keywords:
  - "Computer Vision: Transfer, low-shot, semi- and un- supervised learning"
  - "Computer Vision: Multimodal learning"
---

# A₃B₂: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning

Yiyun Zhou, Zhonghua Jiang, Wenkang Han, Kunxi Li, Mingjing Xu, Chang Yao, Jingyuan Chen

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 2136-2144. DOI: [10.24963/ijcai.2026/238](https://doi.org/10.24963/ijcai.2026/238)

## Abstract

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 A₃B₂, an Adaptive Asymmetric Adapter that alleviates Branch Bias in few-shot learning. A₃B₂ 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, A₃B₂ adopts a lightweight asymmetric design inspired by mixture-of-experts with Load Balancing Regularization. Extensive experiments demonstrate that A₃B₂ consistently outperforms 11 competitive prompt- and adapter-based baselines.