现代信息科技2025，Vol.9Issue(11)：49-53,58,6.DOI:10.19850/j.cnki.2096-4706.2025.11.010
ICAF:具有插值一致性和自适应筛选的无监督持续学习
ICAF:Unsupervised Continual Learning with Interpolation Consistency and Adaptive Filtering
摘要
Abstract
Unsupervised Continual Learning addresses the challenge of sequentially learning tasks without supervision information.However,this setting often leads to catastrophic forgetting.To overcome this issue,memory banks are used to store samples from past tasks.However,storing and replaying appropriate samples is a complex task,and the simple and commonly used random selection is not effective,especially for long-sequence tasks with large-scale samples.To solve this issue,an Unsupervised Continual Learning method with Interpolation Consistency and Adaptive Memory Filtering(ICAF)is proposed.It can effectively select high-quality samples by using the features learned from randomly augmented samples,adjust the threshold during training,and achieve interpolation consistency through a specially designed linear interpolation and data combination strategy,thereby preventing insufficient learning caused by relying solely on interpolated samples from past tasks.This method has achieved the best results on multiple experimental datasets.关键词
持续学习/无监督学习/表示学习/对比学习/自监督学习Key words
Continual Learning/Unsupervised Learning/Representation Learning/Contrastive Learning/Self-supervised Learning分类
信息技术与安全科学引用本文复制引用
叶根诚,王翔..ICAF:具有插值一致性和自适应筛选的无监督持续学习[J].现代信息科技,2025,9(11):49-53,58,6.基金项目
中央高校基本科研业务费专项资金(20119jbz110) （20119jbz110）
国家自然科学基金项目(62176020) （62176020）
国家重点研发计划项目(2020AAA0106800) （2020AAA0106800）
北京市自然科学基金项目L211016 （）
中国科学院(OEIP-O-202004) （OEIP-O-202004）
