Combining Domain-Specific Meta-Learners in the Parameter Space for Cross-Domain Few-Shot Classification

Abstract

The goal of few-shot classification is to learn a model that can classify novel classes using only a few training examples. Despite the promising results shown by existing meta-learning algorithms in solving the few-shot classification problem, there still remains an important challenge: how to generalize to unseen domains while meta-learning on multiple seen domains? In this paper, we propose an optimization-based meta-learning method, called Combining Domain-Specific Meta-Learners (CosML), that addresses the cross-domain few-shot classification problem. CosML first trains a set of meta-learners, one for each training domain, to learn prior knowledge (i.e., meta-parameters) specific to each domain. The domain-specific meta-learners are then combined in the \emph{parameter space}, by taking a weighted average of their meta-parameters, which is used as the initialization parameters of a task network that is quickly adapted to novel few-shot classification tasks in an unseen domain. Our experiments show that CosML outperforms a range of state-of-the-art methods and achieves strong cross-domain generalization ability.

arXiv commentCode coming soon at https://github.com/shumanpng/CosML

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• How transferable are features in deep neural networks?
• Theoretical Models of Learning to Learn
• Meta-Learning: A Survey
• Few-Shot Learning with Metric-Agnostic Conditional Embeddings
• Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation
• Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
• MxML: Mixture of Meta-Learners for Few-Shot Classification