DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning

arXiv:2403.17503v1 Announce Type: new
Abstract: Class-incremental learning (CIL) under an exemplar-free constraint has presented a significant challenge. Existing methods adhering to this constraint are prone to catastrophic forgetting, far more so than replay-based techniques that retain access to past samples. In this paper, to solve the exemplar-free CIL problem, we propose a Dual-Stream Analytic Learning (DS-AL) approach. The DS-AL contains a main stream offering an analytical (i.e., closed-form) linear solution, and a compensation stream improving the inherent under-fitting limitation due …

arxiv class cs.cv cs.lg free incremental type