Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier

01/03/2021
by   Arkabandhu Chowdhury, et al.
2

Recent papers have suggested that transfer learning can outperform sophisticated meta-learning methods for few-shot image classification. We take this hypothesis to its logical conclusion, and suggest the use of an ensemble of high-quality, pre-trained feature extractors for few-shot image classification. We show experimentally that a library of pre-trained feature extractors combined with a simple feed-forward network learned with an L2-regularizer can be an excellent option for solving cross-domain few-shot image classification. Our experimental results suggest that this simpler sample-efficient approach far outperforms several well-established meta-learning algorithms on a variety of few-shot tasks.

READ FULL TEXT

page 8

page 11

research
05/07/2021

Few-Shot Learning for Image Classification of Common Flora

The use of meta-learning and transfer learning in the task of few-shot i...
research
06/19/2020

Self-Supervised Prototypical Transfer Learning for Few-Shot Classification

Most approaches in few-shot learning rely on costly annotated data relat...
research
05/07/2021

ResMLP: Feedforward networks for image classification with data-efficient training

We present ResMLP, an architecture built entirely upon multi-layer perce...
research
05/17/2021

Deep Metric Learning for Few-Shot Image Classification: A Selective Review

Few-shot image classification is a challenging problem which aims to ach...
research
08/31/2022

NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results

We present the design and baseline results for a new challenge in the Ch...
research
01/22/2020

Optimized Generic Feature Learning for Few-shot Classification across Domains

To learn models or features that generalize across tasks and domains is ...
research
06/17/2020

Improving Few-Shot Visual Classification with Unlabelled Examples

We propose a transductive meta-learning method that uses unlabelled inst...

Please sign up or login with your details

Forgot password? Click here to reset