The general framework for few-shot learning by kernel HyperNetworks
Open Access
- 20 May 2023
- journal article
- research article
- Published by Springer Nature in Machine Vision and Applications
- Vol. 34 (4) , 1-16
Abstract
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 the general framework for few-shot learning via kernel HyperNetworks—the fusion of kernels and hypernetwork paradigm. Firstly, we introduce the classical realization of this framework, dubbed HyperShot. Compared to reference approaches that apply a gradient-based adjustment of the parameters, our models aim 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 the support examples’ embeddings instead of the backbone models’ direct feature values. Thanks to this approach, our model can adapt to highly different tasks. While such a method obtains very good results, it is limited by typical problems such as poorly quantified uncertainty due to limited data size. We further show that incorporating Bayesian neural networks into our general framework, an approach we call BayesHyperShot, solves this issue.Keywords
Funding Information
- Narodowe Centrum Nauki (2022/45/N/ST6/03374, 2019/33/B/ST6/00894, 2020/37/B/ST6/03463)
This publication has 25 references indexed in Scilit:
- Uncertainty in Model-Agnostic Meta-Learning using Variational Inference2020
- Boosting Few-Shot Visual Learning With Self-Supervision2019
- Meta-Learning With Differentiable Convex Optimization2019
- Learning to Compare: Relation Network for Few-Shot Learning2018
- Few-Shot Image Recognition by Predicting Parameters from Activations2018
- EMNIST: Extending MNIST to handwritten letters2017
- Generating Sentences from a Continuous Space2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Gaussian Processes in Machine Learning2004
- Learning to Control Fast-Weight Memories: An Alternative to Dynamic Recurrent NetworksNeural Computation, 1992