LSFSL: Leveraging Shape Information in Few-shot Learning
This addresses robustness and generalization issues in few-shot learning, which is incremental as it builds on prior work by incorporating shape priors.
The paper tackles the problem of shortcut learning and texture bias in few-shot learning by proposing LSFSL, which leverages implicit prior information to learn more generalizable features, resulting in models less vulnerable to alterations in color schemes, statistical correlations, and adversarial perturbations.
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.