Diversity with Cooperation: Ensemble Methods for Few-Shot Classification

03/27/2019
by   Nikita Dvornik, et al.
12

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/17/2020

Meta-Meta-Classification for One-Shot Learning

We present a new approach, called meta-meta-classification, to learning ...
research
02/23/2021

Lessons from Chasing Few-Shot Learning Benchmarks: Rethinking the Evaluation of Meta-Learning Methods

In this work we introduce a simple baseline for meta-learning. Our uncon...
research
09/19/2013

A Comparative Analysis of Ensemble Classifiers: Case Studies in Genomics

The combination of multiple classifiers using ensemble methods is increa...
research
09/11/2019

Few-Shot Classification on Unseen Domains by Learning Disparate Modulators

Although few-shot learning studies have advanced rapidly with the help o...
research
01/13/2022

Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning

Modern deep learning requires large-scale extensively labelled datasets ...
research
03/01/2021

Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning

In many real-world problems, collecting a large number of labeled sample...
research
02/19/2019

Adaptive Cross-Modal Few-Shot Learning

Metric-based meta-learning techniques have successfully been applied to ...

Please sign up or login with your details

Forgot password? Click here to reset