HyperShot: Few-Shot Learning by Kernel HyperNetworks
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.
Code (1)
Tasks
Few-Shot Image ClassificationFew-Shot LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On Infinite-Width Hypernetworks
{\em Hypernetworks} are architectures that produce the weights of a task-specific {\em primary network}. A notable application of hypernetworks in the recent literature involves learning to output functional representati…
Meta-LearningInvestigating the Effectiveness of HyperTuning via Gisting
Gisting (Mu et al., 2023) is a simple method for training models to compress information into fewer token representations using a modified attention mask, and can serve as an economical approach to training Transformer-b…
Generalizing Supervised Deep Learning MRI Reconstruction to Multiple and Unseen Contrasts using Meta-Learning Hypernetworks
Meta-learning has recently been an emerging data-efficient learning technique for various medical imaging operations and has helped advance contemporary deep learning models. Furthermore, meta-learning enhances the knowl…
Image ReconstructionInductive BiasMeta-LearningMRI Reconstruction+1Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA
Particle-based Bayesian deep learning often requires a similarity metric to compare two networks. However, naive similarity metrics lack permutation invariance and are inappropriate for comparing networks. Centered Kerne…
Deep LearningDiversityOutlier DetectionUncertainty QuantificationUnderstanding and Simplifying One-Shot Architecture Search
There is growing interest in automating neural network architecture design. Existing architecture search methods can be computationally expensive, requiring thousands of different architectures to be trained from sc…
Neural Architecture Searchreinforcement-learningReinforcement LearningReinforcement Learning (RL)