arXiv 2403.135222025-12-17cs.LGcs.CV

REAL：基于表征增强的无实例类增量学习

REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learning

Shien-Ming Wu School of Intelligent Engineering（申铭武智能工程学院）；School of Future Technology（未来技术学院）；Department of Electrical and Electronic Engineering（电气与电子工程系）

Run He, Di Fang, Yizhu Chen, Kai Tong, Cen Chen, Yi Wang, Lap-pui Chau, Huiping Zhuang

备注：: 13 pages, 7 figures. This paper is published in Knowledge-based System
DOI：: 10.1016/j.knosys.2025.114901

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

REAL通过双流预训练和表征增强蒸馏提升无实例类增量学习的表征能力，结合特征融合缓冲器更高效利用主干网络知识，实现更优的分类性能。

摘要：

无实例类增量学习（EFCIL）旨在通过不依赖历史训练样本作为实例来缓解类增量学习（CIL）中的灾难性遗忘问题。与依赖实例的CIL方法相比，EFCIL更容易出现遗忘问题。最近，一种名为分析持续学习（ACL）的新EFCIL分支引入了递归最小二乘法的无梯度范式，通过在CIL过程中冻结主干网络实现遗忘抵抗的分类器训练。然而，现有的ACL方法存在表征不充分和主干知识利用不足的问题。在本文中，我们提出了基于表征增强的分析学习（REAL）以解决这些问题。为了增强表征，REAL构建了双流基础预训练，随后进行表征增强蒸馏过程。双流基础预训练结合了自监督对比学习用于通用特征和监督学习用于类别特定知识，随后通过表征增强蒸馏将两者合并，增强后续CIL范式的表征。为了利用更多主干网络的知识，REAL提出了一个特征融合缓冲器，用于多层主干网络特征，为后续分类器训练提供信息丰富的特征。我们的方法可以整合到现有的ACL技术中，并提供更具竞争力的性能。实验结果表明，REAL在CIFAR-100、ImageNet-100和ImageNet-1k基准上实现了最先进的性能，优于无实例方法并在与实例方法的竞争中表现优异。

英文摘要：

Exemplar-free class-incremental learning (EFCIL) aims to mitigate catastrophic forgetting in class-incremental learning (CIL) without available historical training samples as exemplars. Compared with its exemplar-based CIL counterpart that stores exemplars, EFCIL suffers more from forgetting issues. Recently, a new EFCIL branch named Analytic Continual Learning (ACL) introduces a gradient-free paradigm via Recursive Least-Square, achieving a forgetting-resistant classifier training with a frozen backbone during CIL. However, existing ACL suffers from ineffective representations and insufficient utilization of backbone knowledge. In this paper, we propose a representation-enhanced analytic learning (REAL) to address these problems. To enhance the representation, REAL constructs a dual-stream base pretraining followed by representation enhancing distillation process. The dual-stream base pretraining combines self-supervised contrastive learning for general features and supervised learning for class-specific knowledge, followed by the representation enhancing distillation to merge both streams, enhancing representations for subsequent CIL paradigm. To utilize more knowledge from the backbone, REAL presents a feature fusion buffer to multi-layer backbone features, providing informative features for the subsequent classifier training. Our method can be incorporated into existing ACL techniques and provides more competitive performance. Empirical results demonstrate that, REAL achieves state-of-the-art performance on CIFAR-100, ImageNet-100 and ImageNet-1k benchmarks, outperforming exemplar-free methods and rivaling exemplar-based approaches.

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。