arXiv cs.AI· Wenju Sun, Qingyong Li, Boyang Li, Wen Wang, Siyu Zhang, Yi Wei, Yangliao Geng·· 2 天前AI 评分22
Co2In：结合知识编码、巩固与整合的双层记忆增量学习框架
Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration
AI 导读
受人类记忆机制启发，研究者提出增量学习框架 Co2In，采用工作记忆与长期记忆协同的双层架构，通过知识编码、巩固与整合实现高可塑性与稳定性的平衡。在 CIFAR-10、CIFAR-100 和 Tiny-ImageNet 的无样本 Class-IL 与 Task-IL 设置下，Co2In 取得 SOTA 性能且内存消耗高效。该工作已被 IEEE TPAMI 接收。
正文 · 原文
Abstract:Incremental learning (IL) aims to continually acquire new knowledge (plasticity) while retaining previously learned information (stability). However, striking a balance between plasticity and stability remains a significant challenge for intelligent systems. The human brain achieves exceptional balance, owing to various memory units that collaboratively encode and store information. Inspired by human memory mechanisms, this paper introduces an IL framework with knowledge enCoding, Consolidation, and Integration (Co2In). Co2In is designed as a bi-level memory architecture: a working memory for adaptive knowledge acquisition and a long-term memory dedicated to the persistent retention of information. The two memory modules work cooperatively during IL. The working memory first learns from new data to encode knowledge into parameters. Subsequently, Co2In performs a consolidation process to identify underlying patterns in the learned parameters and re-express them into a compact knowledge representation. Next, the knowledge representation and the identified patterns are transformed into separate network layers and integrated into the long-term memory. These designs empower Co2In to accumulate knowledge with high plasticity and stability. We evaluate Co2In on CIFAR-10, CIFAR-100, and Tiny-ImageNet under exemplar-free Class-IL and Task-IL settings. Experimental results show that Co2In achieves state-of-the-art performance with efficient memory consumption.
| Comments: | Accepted by IEEE Transactions On Pattern Analysis and Machine Intelligence |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.21804 [cs.AI] |
| (or arXiv:2610.21804v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21804 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: WenJu Sun [view email]
[v1]
Thu, 15 Oct 2026 12:54:15 UTC (11,548 KB)
来源：arXiv cs.AI · arxiv.org