Few-Shot Class-Incremental Learning via Feature Space Composition release_voqnl3sfxzhy7mf6iqcopndxei

by Hanbin Zhao, Yongjian Fu, Xuewei Li, Songyuan Li, Bourahla Omar, Xi Li

Released as a article .

2020  

Abstract

As a challenging problem in machine learning, few-shot class-incremental learning asynchronously learns a sequence of tasks, acquiring the new knowledge from new tasks (with limited new samples) while keeping the learned knowledge from previous tasks (with old samples discarded). In general, existing approaches resort to one unified feature space for balancing old-knowledge preserving and new-knowledge adaptation. With a limited embedding capacity of feature representation, the unified feature space often makes the learner suffer from semantic drift or overfitting as the number of tasks increases. With this motivation, we propose a novel few-shot class-incremental learning pipeline based on a composite representation space, which makes old-knowledge preserving and new-knowledge adaptation mutually compatible by feature space composition (enlarging the embedding capacity). The composite representation space is generated by integrating two space components (i.e. stable base knowledge space and dynamic lifelong-learning knowledge space) in terms of distance metric construction. With the composite feature space, our method performs remarkably well on the CUB200 and CIFAR100 datasets, outperforming the state-of-the-art algorithms by 10.58% and 14.65% respectively.
In text/plain format

Archived Files and Locations

application/pdf  1.7 MB
file_gevl6ngxbfauhpwr3lmkv3ank4
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-06-28
Version   v1
Language   en ?
arXiv  2006.15524v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 7958c438-71ff-4da9-9427-b8080894161b
API URL: JSON