Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?

03/25/2020
by   Yonglong Tian, et al.
27

The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost. Few-shot learning is widely used as one of the standard benchmarks in meta-learning. In this work, we show that a simple baseline: learning a supervised or self-supervised representation on the meta-training set, followed by training a linear classifier on top of this representation, outperforms state-of-the-art few-shot learning methods. An additional boost can be achieved through the use of self-distillation. This demonstrates that using a good learned embedding model can be more effective than sophisticated meta-learning algorithms. We believe that our findings motivate a rethinking of few-shot image classification benchmarks and the associated role of meta-learning algorithms. Code is available at: http://github.com/WangYueFt/rfs/.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/30/2019

Meta-learning algorithms for Few-Shot Computer Vision

Few-Shot Learning is the challenge of training a model with only a small...
research
02/22/2021

MetaDelta: A Meta-Learning System for Few-shot Image Classification

Meta-learning aims at learning quickly on novel tasks with limited data ...
research
12/24/2021

Does MAML Only Work via Feature Re-use? A Data Centric Perspective

Recent work has suggested that a good embedding is all we need to solve ...
research
06/17/2020

Self-supervised Knowledge Distillation for Few-shot Learning

Real-world contains an overwhelmingly large number of object classes, le...
research
11/14/2019

Self-Supervised Learning For Few-Shot Image Classification

Few-shot image classification aims to classify unseen classes with limit...
research
10/25/2021

Multi-Task Meta-Learning Modification with Stochastic Approximation

Meta-learning methods aim to build learning algorithms capable of quickl...
research
03/09/2020

A New Meta-Baseline for Few-Shot Learning

Meta-learning has become a popular framework for few-shot learning in re...

Please sign up or login with your details

Forgot password? Click here to reset