AI RESEARCH
Grow, Assess, Compress: Adaptive Backbone Scaling for Memory-Efficient Class Incremental Learning
arXiv CS.LG
•
ArXi:2603.08426v1 Announce Type: new Class Incremental Learning (CIL) poses a fundamental challenge: maintaining a balance between the plasticity required to learn new tasks and the stability needed to prevent catastrophic forgetting. While expansion-based methods effectively mitigate forgetting by adding task-specific parameters, they suffer from uncontrolled architectural growth and memory overhead. In this paper, we propose a novel dynamic scaling framework that adaptively manages model capacity through a cyclic "GRow, Assess, ComprEss" (GRACE) strategy.