Due to the limited availability of data, existing few-shot learning methods trained from scratch fail to achieve satisfactory performance. In contrast, large-scale pre-trained models such as CLIP demonstrate remarkable few-shot and zero-shot capabilities. To enhance the performance of pre-trained models for downstream tasks, fine-tuning the model on downstream data is frequently necessary. However, fine-tuning the pre-trained model leads to a decrease in its generalizability in the presence of distribution shift, while the limited number of samples in few-shot learning makes the model highly susceptible to overfitting. Consequently, existing methods for fine-tuning few-shot learning primarily focus on fine-tuning the model's classification head or introducing additional structure. In this paper, we introduce a fine-tuning approach termed Feature Discrimination Alignment (FD-Align). Our method aims to bolster the model's generalizability by preserving the consistency of spurious features across the fine-tuning process. Extensive experimental results validate the efficacy of our approach for both ID and OOD tasks. Once fine-tuned, the model can seamlessly integrate with existing methods, leading to performance improvements. Our code can be found in https://github.com/skingorz/FD-Align.

翻译：由于数据可用性有限，现有从零训练的小样本学习方法难以达到令人满意的性能。相比之下，CLIP等大规模预训练模型展现出卓越的小样本和零样本能力。为提升预训练模型在下游任务中的表现，通常需要在下游数据上对其进行微调。然而，微调预训练模型会使其在遇到分布偏移时泛化能力下降，而小样本学习中的有限样本更使模型极易过拟合。因此，现有小样本微调方法主要聚焦于调整模型分类头或引入额外结构。本文提出一种名为特征判别对齐（FD-Align）的微调方法。该方法旨在通过保持微调过程中虚假特征的一致性来增强模型的泛化能力。大量实验结果验证了本方法在ID（同分布）和OOD（分布外）任务中的有效性。微调后的模型可与现有方法无缝集成，进而实现性能提升。我们的代码可在 https://github.com/skingorz/FD-Align 获取。