Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning

TL;DR

This paper introduces TEAM, a novel transductive episodic-wise adaptive metric framework that combines meta-learning, deep metric learning, and transductive inference to improve few-shot learning by tailoring task-specific metrics.

Contribution

The paper proposes a new method that formulates task adaptation as a semi-definite programming problem with a closed-form solution, enhancing few-shot learning performance.

Findings

Achieves state-of-the-art results on three benchmark datasets.

Effectively adapts shared embeddings into discriminative task-specific metrics.

Outperforms existing approaches in few-shot learning tasks.

Abstract

Few-shot learning, which aims at extracting new concepts rapidly from extremely few examples of novel classes, has been featured into the meta-learning paradigm recently. Yet, the key challenge of how to learn a generalizable classifier with the capability of adapting to specific tasks with severely limited data still remains in this domain. To this end, we propose a Transductive Episodic-wise Adaptive Metric (TEAM) framework for few-shot learning, by integrating the meta-learning paradigm with both deep metric learning and transductive inference. With exploring the pairwise constraints and regularization prior within each task, we explicitly formulate the adaptation procedure into a standard semi-definite programming problem. By solving the problem with its closed-form solution on the fly with the setup of transduction, our approach efficiently tailors an episodic-wise metric for each task to adapt all features from a shared task-agnostic embedding space into a more discriminative task-specific metric space. Moreover, we further leverage an attention-based bi-directional similarity strategy for extracting the more robust relationship between queries and prototypes. Extensive experiments on three benchmark datasets show that our framework is superior to other existing approaches and achieves the state-of-the-art performance in the few-shot literature.