Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using fewer samples, analogous to how humans learn from limited experience. In this limited-data scenario, the challenges associated with deep neural networks, such as shortcut learning and texture bias behaviors, are further exacerbated. Moreover, the significance of addressing shortcut learning is not yet fully explored in the few-shot setup. To address these issues, we propose LSFSL, which enforces the model to learn more generalizable features utilizing the implicit prior information present in the data. Through comprehensive analyses, we demonstrate that LSFSL-trained models are less vulnerable to alteration in color schemes, statistical correlations, and adversarial perturbations leveraging the global semantics in the data. Our findings highlight the potential of incorporating relevant priors in few-shot approaches to increase robustness and generalization.

翻译：少样本学习技术旨在像人类从有限经验中学习一样，利用更少的样本挖掘数据中的潜在模式。在数据有限的场景中，深度神经网络面临的挑战（如捷径学习和纹理偏差行为）进一步加剧。此外，在少样本设置下，处理捷径学习问题的重要性尚未得到充分探索。为解决这些问题，我们提出LSFSL方法，通过利用数据中隐含的先验信息，迫使模型学习更具泛化能力的特征。通过全面分析，我们证明基于LSFSL训练的模型借助数据中的全局语义，对颜色方案改变、统计相关性及对抗性扰动的敏感性更低。我们的研究结果凸显了在少样本方法中融入相关先验信息以提升鲁棒性和泛化能力的潜力。