A₃B₂：一种自适应非对称适配器，用于缓解视觉-语言图像分类中的分支偏差
A$_3$B$_2$: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning
AI总结：
本文提出A₃B₂适配器，通过引入不确定性感知适配器阻尼机制，缓解少样本学习中的分支偏差问题，实验表明其在多个数据集上优于现有基线方法。
摘要：
高效的迁移学习方法为大规模视觉-语言模型（例如CLIP）提供了强大的少样本迁移能力，但现有适配方法遵循固定微调范式，隐含假设图像和文本分支的重要性是均匀的，这一假设在图像分类中未被系统研究。通过深入分析，我们揭示了视觉-语言图像分类中的分支偏差问题：在分布外设置下，适配图像编码器并不总能提高性能。受此启发，我们提出了A₃B₂，一种自适应非对称适配器，用于缓解少样本学习中的分支偏差。A₃B₂引入了不确定性感知适配器阻尼（UAAD），在预测不确定性较高时自动抑制图像分支适配，实现软且数据驱动的控制，无需手动干预。在架构上，A₃B₂采用了一种轻量级非对称设计，受混合专家启发，结合负载平衡正则化。在三个少样本图像分类任务上，对11个数据集的广泛实验表明，A₃B₂在多个数据集上一致优于11个竞争的提示和适配基线方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
