HyperShot: Few-Shot Learning by Kernel HyperNetworks
This work addresses the problem of few-shot learning for machine learning practitioners by introducing an incremental improvement that enhances adaptability across diverse tasks.
The paper tackles the challenge of few-shot learning, particularly in the one-shot setting, by proposing HyperShot, a method that fuses kernels and hypernetworks to adapt classifier parameters based on task embeddings, achieving competitive performance on benchmark datasets.
Few-shot models aim at making predictions using a minimal number of labeled examples from a given task. The main challenge in this area is the one-shot setting where only one element represents each class. We propose HyperShot - the fusion of kernels and hypernetwork paradigm. Compared to reference approaches that apply a gradient-based adjustment of the parameters, our model aims to switch the classification module parameters depending on the task's embedding. In practice, we utilize a hypernetwork, which takes the aggregated information from support data and returns the classifier's parameters handcrafted for the considered problem. Moreover, we introduce the kernel-based representation of the support examples delivered to hypernetwork to create the parameters of the classification module. Consequently, we rely on relations between embeddings of the support examples instead of direct feature values provided by the backbone models. Thanks to this approach, our model can adapt to highly different tasks.