Qingyong Li

MOBO: A Merging-Oriented Bi-Level Optimization Framework for Class Incremental Learning

Co$^{2}$ In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration.

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 (Co $^{2}$ In). Co $^{2}$ In 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, Co $^{2}$ In 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 Co $^{2}$ In to accumulate knowledge with high plasticity and stability. We evaluate Co $^{2}$ In on CIFAR-10, CIFAR-100, and Tiny-ImageNet under exemplar-free Class-IL and Task-IL settings. Experimental results show that Co $^{2}$ In achieves state-of-the-art performance with efficient memory consumption.