Learning to Compare: Relation Network for Few-Shot Learning

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 lear...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 1199 - 1208
Main Authors Sung, Flood, Yang, Yongxin, Zhang, Li, Xiang, Tao, Torr, Philip H.S., Hospedales, Timothy M.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Computer architecture
Image recognition
Measurement
Recurrent neural networks
Task analysis
Training
Online AccessGet full text

Cover

More Information
Summary: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 five benchmarks demonstrate that our simple approach provides a unified and effective approach for both of these two tasks.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00131