Towards Plastic and Stable Exemplar-Free Incremental Learning: A Dual-Learner Framework with Cumulative Parameter Averaging

arXiv:2310.18639v3 Announce Type: replace
Abstract: The dilemma between plasticity and stability presents a significant challenge in Incremental Learning (IL), especially in the exemplar-free scenario where accessing old-task samples is strictly prohibited during the learning of a new task. A straightforward solution to this issue is learning and storing an independent model for each task, known as Single Task Learning (STL). Despite the linear growth in model storage with the number of tasks in STL, we empirically discover that averaging these …

abstract arxiv challenge cs.cv framework free incremental issue plastic samples solution stability type