SWIS: Self-Supervised Representation Learning For Writer independent offline Signature Verification

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 have 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.