Interpretable Concept-based Prototypical Networks for Few-Shot Learning
It addresses the need for interpretability in few-shot learning, which is crucial for deploying trustworthy AI systems, though it is incremental as it matches rather than surpasses existing methods.
The paper tackles the problem of few-shot learning by proposing an interpretable method based on human-understandable concepts, achieving performance comparable to six state-of-the-art black-box methods on the CUB dataset.
Few-shot learning aims at recognizing new instances from classes with limited samples. This challenging task is usually alleviated by performing meta-learning on similar tasks. However, the resulting models are black-boxes. There has been growing concerns about deploying black-box machine learning models and FSL is not an exception in this regard. In this paper, we propose a method for FSL based on a set of human-interpretable concepts. It constructs a set of metric spaces associated with the concepts and classifies samples of novel classes by aggregating concept-specific decisions. The proposed method does not require concept annotations for query samples. This interpretable method achieved results on a par with six previously state-of-the-art black-box FSL methods on the CUB fine-grained bird classification dataset.