arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2111.11208cs.LGcs.AI
收藏

自监督类增量学习

Self-Supervised Class Incremental Learning

Zhejiang University(浙江大学)

Zixuan Ni, Siliang Tang, Yueting Zhuang

摘要:

现有的类增量学习(CIL)方法是基于对数据标签敏感的监督分类框架。当基于新的类数据更新它们时,它们遭受灾难性遗忘:模型不能清楚地区分旧类数据和新类数据。在本文中,我们首次探讨了类增量学习(SSCIL)中的自监督表示学习的性能,它丢弃了数据标签和模型的分类器。为了全面讨论CIL中监督和自监督方法之间的性能差异,我们设置了三种不同的类增量方案:随机类方案,语义类方案和聚类方案,以模拟各种类增量学习场景。此外,我们提出了线性评估协议(LEP)和泛化评估协议(GEP)来衡量模型在CIL中的表示、分类能力和泛化能力。我们的实验(在ImageNet-100和ImageNet上)表明,SSCIL比CIL中的监督策略具有更好的抗遗忘能力和鲁棒性。为了理解是什么导致了SSCIL中的灾难性遗忘,我们研究了SSCIL的主要组成部分,并得出结论:(1)不同数据增强的组合提高了模型的表示质量,\textit{Grayscale}操作降低了SSCIL中数据增强的系统噪声。(2)投影器类似于缓冲器,减少了SSCIL中模型的不必要的参数更新,并增加了模型的鲁棒性。尽管SSCIL的性能明显高于CIL中的监督方法,但与联合学习仍有明显的差距。我们的探索提供了一个基线的自监督类增量学习的大规模数据集,并提供了一些前瞻性的策略,以减轻灾难性遗忘在CIL。

英文摘要:

Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot discern old class data clearly from the new. In this paper, we explore the performance of Self-Supervised representation learning in Class Incremental Learning (SSCIL) for the first time, which discards data labels and the model's classifiers. To comprehensively discuss the difference in performance between supervised and self-supervised methods in CIL, we set up three different class incremental schemes: Random Class Scheme, Semantic Class Scheme, and Cluster Scheme, to simulate various class incremental learning scenarios. Besides, we propose Linear Evaluation Protocol (LEP) and Generalization Evaluation Protocol (GEP) to metric the model's representation classification ability and generalization in CIL. Our experiments (on ImageNet-100 and ImageNet) show that SSCIL has better anti-forgetting ability and robustness than supervised strategies in CIL. To understand what alleviates the catastrophic forgetting in SSCIL, we study the major components of SSCIL and conclude that (1) the composition of different data augmentation improves the quality of the model's representation and the \textit{Grayscale} operation reduces the system noise of data augmentation in SSCIL. (2) the projector, like a buffer, reduces unnecessary parameter updates of the model in SSCIL and increases the robustness of the model. Although the performance of SSCIL is significantly higher than supervised methods in CIL, there is still an apparent gap with joint learning. Our exploration gives a baseline of self-supervised class incremental learning on large-scale datasets and contributes some forward strategies for mitigating the catastrophic forgetting in CIL.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑