Learning to Compare: Relation Network for Few-Shot Learning

11/16/2017
by   Flood Sung, et al.
0

We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained end-to-end from scratch. During meta-learning, it learns to learn a deep distance metric to compare a small number of images within episodes, each of which is designed to simulate the few-shot setting. Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network. Besides providing improved performance on few-shot learning, our framework is easily extended to zero-shot learning. Extensive experiments on four datasets demonstrate that our simple approach provides a unified and effective approach for both of these two tasks.

READ FULL TEXT
research
03/15/2017

Prototypical Networks for Few-shot Learning

We propose prototypical networks for the problem of few-shot classificat...
research
09/17/2020

'Less Than One'-Shot Learning: Learning N Classes From M<N Samples

Deep neural networks require large training sets but suffer from high co...
research
09/10/2019

PARN: Position-Aware Relation Networks for Few-Shot Learning

Few-shot learning presents a challenge that a classifier must quickly ad...
research
02/29/2020

Learning to Compare Relation: Semantic Alignment for Few-Shot Learning

Few-shot learning is a fundamental and challenging problem since it requ...
research
02/10/2018

Combinets: Learning New Classifiers via Recombination

Problems with few examples of a new class of objects prove challenging t...
research
05/04/2020

Generalized Reinforcement Meta Learning for Few-Shot Optimization

We present a generic and flexible Reinforcement Learning (RL) based meta...
research
10/31/2022

Learning New Tasks from a Few Examples with Soft-Label Prototypes

It has been experimentally demonstrated that humans are able to learn in...

Please sign up or login with your details

Forgot password? Click here to reset