# Diversity with Cooperation: Ensemble Methods for Few-Shot Classification

## TL;DR

This paper introduces an ensemble-based approach for few-shot classification that leverages classifier diversity and cooperation to significantly outperform existing meta-learning methods, achieving state-of-the-art results.

## Contribution

It proposes a novel ensemble strategy addressing high variance in few-shot classifiers, emphasizing cooperation and diversity to improve performance.

## Key findings

- Ensemble methods outperform meta-learning techniques in few-shot classification.
- Single networks via distillation can achieve state-of-the-art results.
- Addressing classifier variance is key to improving few-shot learning.

## Abstract

Few-shot classification consists of learning a predictive model that is able to effectively adapt to a new class, given only a few annotated samples. To solve this challenging problem, meta-learning has become a popular paradigm that advocates the ability to "learn to adapt". Recent works have shown, however, that simple learning strategies without meta-learning could be competitive. In this paper, we go a step further and show that by addressing the fundamental high-variance issue of few-shot learning classifiers, it is possible to significantly outperform current meta-learning techniques. Our approach consists of designing an ensemble of deep networks to leverage the variance of the classifiers, and introducing new strategies to encourage the networks to cooperate, while encouraging prediction diversity. Evaluation is conducted on the mini-ImageNet and CUB datasets, where we show that even a single network obtained by distillation yields state-of-the-art results.